0.5.2/doc/pguide-en.html

<?xml version="1.0" encoding="UTF-8"?>

<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">

<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">

<head>
<meta http-equiv="Content-Language" content="en" />
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
<meta http-equiv="Content-Style-Type" content="text/css" />
<meta name="author" content="Mikio Hirabayashi" />
<meta name="keywords" content="Hyper Estraier, Estraier, full-text search, API" />
<meta name="description" content="API specifications of Hyper Estraier" />
<link rel="contents" href="./" />
<link rel="alternate" href="pguide-ja.html" hreflang="ja" title="the Japanese version" />
<link rel="stylesheet" href="common.css" />
<link rel="icon" href="icon16.png" />
<link rev="made" href="mailto:mikio@users.sourceforge.net" />
<title>Programming Guide of Hyper Estraier Version 1</title>
</head>

<body>

<h1>Programming Guide</h1>

<div class="note">Copyright (C) 2004-2005 Mikio Hirabayashi</div>
<div class="note">Last Update: Tue, 07 Jun 2005 06:17:00 +0900</div>
<div class="navi">[<a href="pguide-ja.html" hreflang="ja">Japanese</a>] [<a href="index.html">HOME</a>]</div>

<hr />

<h2 id="tableofcontents">Table of Contents</h2>

<ol>
<li><a href="#introduction">Introduction</a></li>
<li><a href="#architecture">Architecture</a></li>
<li><a href="#building">Building</a></li>
<li><a href="#estdoc">API for Documents</a></li>
<li><a href="#estcond">API for Search Conditions</a></li>
<li><a href="#estdb">API for Database</a></li>
<li><a href="#gatherer">Example of Gatherer</a></li>
<li><a href="#searcher">Example of Searcher</a></li>
<li><a href="#paralleling">Paralleling</a></li>
</ol>

<hr />

<h2 id="introduction">Introduction</h2>

<p>This document describes how to use the API of Hyper Estraier.  If you have never read <a href="uguide-en.html">the user's guide</a> yet, please do it beforehand.</p>

<p>The API enables to realize many requirements which is impossible with `estcmd' and `estsearch.cgi' only.  Whlie `estcmd' can handle documents as files, it is possible to make an application to handle records in a relational database as a document by using the library.  While `estseek.cgi' is accessed with a web browser, it is possible to make an application with a GUI based on the native OS.</p>

<p>The core API of Hyper Estraier provides some functions to manage the inverted index only.  That is, processes of retrieving documents and calculating them are assigned to an application.  Also, processes to display the search result is assigned to the application.  Consequently, Hyper Estraier does not depend on any document repository, any file format, nor any user interface.  They can be selected by the author of the application.</p>

<p>Hyper Estraier handles Unicode (UCS-2) and present it as UTF-8.  That is, most languages in the current world is available.  Moreover, because keys of search are extracted from the body text by N-gram method, Hyper Estraier does not depend on any vocabulary.</p>

<p>One of characteristics of Hyper Estraier is high scalability.  So, the author of the application does not need to consider the scalability as long as using the API of Hyper Estraier.</p>

<p>As this document descibes the core API, Hyper Estraier provides the node API based on P2P architecture.  Refer to <a href="nguide-en.html">the P2P Guide</a> for the node API.</p>

<hr />

<h2 id="architecture">Architecture</h2>

<p>This section describes the arhcitecture of the core API of Hyper Estraier.</p>

<h3>Gatherer and Filter</h3>

<p>The term `gatherer' means functions to register documents to the index.  A gatherer is to be implemented in an application.  For example, `estcmd' has functions to collect documents by scanning the file system.  There are the following procedures.</p>

<ul>
<li>To specifiy the name of the index and the entry point of scanning, by parsing the command line arguments.</li>
<li>To open the index.</li>
<li>To scan the file system and specify the paths of the target files.</li>
<li>For each file of the list above --<ul>
<li>To discriminate the file format by suffix of the name.</li>
<li>To read the file if the format is supported.</li>
<li>To call the filter function corresponding to the format and create a document object.</li>
<li>To register the document object into the index.</li>
</ul></li>
<li>To close the index.</li>
</ul>

<p>The term `filter' means functions to extract attributes and body text from a file.  A filter is implemented in the application.  While it can be an own implementation of the application, it can be realized by using some existing library.  Moreover, it can be realized by calling an outer command.</p>

<h3>Searcher</h3>

<p>The term `searcher' means functions to search the index for some documents corresponding to conditions specified by users.  A searcher is implemented in the application.  For example, `estseek.cgi' has functions to display the search result as HTML, called as a CGI script by the web server.  There is the following procedures.</p>

<ul>
<li>To read such configurations as the name of the index from the configuration file.</li>
<li>To parse the parameters of CGI and get the search condition specified by the user.</li>
<li>To open the index.</li>
<li>To create a search condition object composed of a search phrase, some attribute expressions, an order expression.</li>
<li>To give the search condition object to the index and get a list of IDs of documents corresponding the conditions.</li>
<li>For each document of the list above --<ul>
<li>To retrieve the document object from the index.</li>
<li>To display attributes and the snippet.</li>
</ul></li>
<li>To close the index.</li>
</ul>

<p>Snippet of the body text is useful for the result to be straightforward.  While a function is provided to create snippet by the API, the application can implement its own function.</p>

<h3>Typical Architecture</h3>

<p>The following is illustration of a typical architecture of the application of Hyper Estraier.  As it is no more than a concept, you can design your own architecture.</p>

<div class="illust"><img src="coreframe.png" width="720" height="550" alt="[framework]" /></div>

<hr />

<h2 id="building">Building</h2>

<p>As Hyper Estraier provides the API for the C language, an application is implemented in C or C++.  This section describes how to build the application with the library of Hyper Estraier.</p>

<h3>Including Headers</h3>

<p>In each source of applications of the core API, include `estraier.h', `cabin.h', and `stdlib.h'.  `estraier.h' is a header file of Hyper Estraier.  `cabin.h' is a header file of QDBM.  See <a href="http://qdbm.sourceforge.net/spex.html#cabinapi">the document of QDBM</a> for the functions provided by `cabin.h'.</p>

<pre>#include &lt;estraier.h&gt;
#include &lt;cabin.h&gt;
#include &lt;stdlib.h&gt;
</pre>

<h3>Compilation and Linking</h3>

<p>By default, headers of Hyper Estraier are installed in `/usr/local/include', and libraries are installed in `/usr/local/lib'.  Other underlying libraries except for `-lestraier' are `-lqdbm', `-lz' `-liconv', `-lm', and `-lc'.  That is, perform the following command to build an application.</p>

<pre>gcc -I/usr/local/include -o foobar foobar.c \
  -L/usr/local/lib -lestraier -lqdbm -lz -liconv -lm -lc
</pre>

<p>However, the above does not works if the destination of installation is different.  It is suggested to use `estconfig' in order to improve maintainability, as the following.</p>

<pre>gcc `estconfig --cflags` -o foobar foobar.c `estconfig --ldflags` `estconfig --libs`
</pre>

<h3>Command for Integration</h3>

<p>`estconfig' is useful for integration of an application or a system using Hyper Estraier.  It outputs setting and configurations of Hyper Estraier.</p>

<dl>
<dt><kbd>estconfig --version</kbd></dt>
<dd>to output version information.</dd>
<dt><kbd>estconfig --prefix</kbd></dt>
<dd>to output the prefix of the destination of installation.</dd>
<dt><kbd>estconfig --execprefix</kbd></dt>
<dd>to output the prefix of the files depending on the platform.</dd>
<dt><kbd>estconfig --headdir</kbd></dt>
<dd>to output the prefix of the headers.</dd>
<dt><kbd>estconfig --libdir</kbd></dt>
<dd>to output the prefix of the libraries.</dd>
<dt><kbd>estconfig --bindir</kbd></dt>
<dd>to output the prefix of the commands.</dd>
<dt><kbd>estconfig --libexecdir</kbd></dt>
<dd>to output the prefix of the CGI script.</dd>
<dt><kbd>estconfig --datadir</kbd></dt>
<dd>to output the prefix of the configuration files.</dd>
<dt><kbd>estconfig --cflags</kbd></dt>
<dd>to output the compiler options to be specified when building.</dd>
<dt><kbd>estconfig --ldflags</kbd></dt>
<dd>to output the linker options to be specified when building.</dd>
<dt><kbd>estconfig --libs</kbd></dt>
<dd>to output the libraries to be specified when building.</dd>
<dt><kbd>estconfig --mtlibs</kbd></dt>
<dd>to output the libraries for applications with multi thread.</dd>
<dt><kbd>estconfig --sklibs</kbd></dt>
<dd>to output the libraries for applications with socket.</dd>
</dl>

<p>`estconfig' always returns 0 as the exit status.</p>

<hr />

<h2 id="estdoc">API for Documents</h2>

<p>The API for documents aims to handle documents which were registered into the index.</p>

<h3>Description</h3>

<p>The type of the structure `ESTDOC' is for abstraction of a document.  A document is composed of some attributes and some text sentences.  No entitiy of `ESTDOC' is accessed directly, but it is accessed by the pointer.  The term of "document object" means the pointer and its referent.  A document object is created by the function `est_doc_new' and destroyed by `est_doc_delete'.  Every created document object should be destroyed.</p>

<p>Target documents of search are to be registered in the database beforehand.  The ID is assigned to each registered document.  When search, they can be retrieved from the database by their ID.  The encoding of attributes and text sentences should be UTF-8.</p>

<p>The following is a typical use case of document object.</p>

<pre>ESTDOC *doc;

/* create a document object */
doc = est_doc_new();

/* add the URI and the title as attributes */
est_doc_add_attr(doc, "@uri", "http://foo.bar/baz.txt");
est_doc_add_attr(doc, "@title", "Now Scream");

/* add text sentences */
est_doc_add_text(doc, "Give it up, Yo!  Give it up, Yo!");
est_doc_add_text(doc, "Check it out, come on!");

  /* register the object or display it here */

/* destroy the object */
est_doc_delete(doc);
</pre>

<h3>API</h3>

<p>The function `est_doc_new' is used in order to create a document object.</p>

<dl>
<dt><kbd>ESTDOC *est_doc_new(void);</kbd></dt>
<dd>The return value is an object of a document.</dd>
</dl>

<p>The function `est_doc_new_from_draft' is used in order to create a document object made from draft data.</p>

<dl>
<dt><kbd>ESTDOC *est_doc_new_from_draft(const char *<var>draft</var>);</kbd></dt>
<dd>`draft' specifies a string of draft data.  The return value is an object of a document.</dd>
</dl>

<p>The function `est_doc_delete' is used in order to destroy a document object.</p>

<dl>
<dt><kbd>void est_doc_delete(ESTDOC *<var>doc</var>);</kbd></dt>
<dd>`doc' specifies a document object.</dd>
</dl>

<p>The function `est_doc_add_attr' is used in order to add an attribute to a document object.</p>

<dl>
<dt><kbd>void est_doc_add_attr(ESTDOC *<var>doc</var>, const char *<var>name</var>, const char *<var>value</var>);</kbd></dt>
<dd>`doc' specifies a document object.  `name' specifies the name of an attribute.  `value' specifies the value of the attribute.  If it is `NULL', the attribute is removed.</dd>
</dl>

<p>The function `est_doc_add_text' is used in order to add a sentence of text to a document object.</p>

<dl>
<dt><kbd>void est_doc_add_text(ESTDOC *<var>doc</var>, const char *<var>text</var>);</kbd></dt>
<dd>`doc' specifies a document object.  `text' specifies a sentence of text.</dd>
</dl>

<p>The function `est_doc_add_hidden_text' is used in order to add a hidden sentence to a document object.</p>

<dl>
<dt><kbd>void est_doc_add_hidden_text(ESTDOC *<var>doc</var>, const char *<var>text</var>);</kbd></dt>
<dd>`doc' specifies a document object.  `text' specifies a hidden sentence.</dd>
</dl>

<p>The function `est_doc_id' is used in order to get the ID number of a document object.</p>

<dl>
<dt><kbd>int est_doc_id(ESTDOC *<var>doc</var>);</kbd></dt>
<dd>`doc' specifies a document object.  The return value is the ID number of the document object.  If the object has never been registered, -1 is returned.</dd>
</dl>

<p>The function `est_doc_attr_names' is used in order to get a list of attribute names of a document object.</p>

<dl>
<dt><kbd>CBLIST *est_doc_attr_names(ESTDOC *<var>doc</var>);</kbd></dt>
<dd>`doc' specifies a document object.  The return value is a new list object of attribute names of the document object.  Because the object of the return value is opened with the function `cblistopen', it should be closed with the function `cblistclose' if it is no longer in use.</dd>
</dl>

<p>The function `est_doc_attr' is used in order to get the value of an attribute of a document object.</p>

<dl>
<dt><kbd>const char *est_doc_attr(ESTDOC *<var>doc</var>, const char *<var>name</var>);</kbd></dt>
<dd>`doc' specifies a document object.  `name' specifies the name of an attribute.  The return value is the value of the attribute or `NULL' if it does not exist.  The life duration of the returned string is synchronous with the one of the document object.</dd>
</dl>

<p>The function `est_doc_texts' is used in order to get a list of sentences of the text of a document object.</p>

<dl>
<dt><kbd>const CBLIST *est_doc_texts(ESTDOC *<var>doc</var>);</kbd></dt>
<dd>`doc' specifies a document object.  The return value is a list object of sentences of the text of the document object.  The life duration of the returned object is synchronous with the one of the document object.</dd>
</dl>

<p>The function `est_doc_cat_texts' is used in order to concatenate sentences of the text of a document object.</p>

<dl>
<dt><kbd>char *est_doc_cat_texts(ESTDOC *<var>doc</var>);</kbd></dt>
<dd>`doc' specifies a document object.  The return value is concatenated sentences of a document object.  Because the region of the return value is allocated with the `malloc' call, it should be released with the `free' call if it is no longer in use.</dd>
</dl>

<p>The function `est_doc_dump_draft' is used in order to dump draft data of a document object.</p>

<dl>
<dt><kbd>char *est_doc_dump_draft(ESTDOC *<var>doc</var>);</kbd></dt>
<dd>`doc' specifies a document object.  The return value is draft data of a document object.  Because the region of the return value is allocated with the `malloc' call, it should be released with the `free' call if it is no longer in use.</dd>
</dl>

<p>The function `est_doc_make_snippet' is used in order to make a snippet of the body text of a document object.</p>

<dl>
<dt><kbd>char *est_doc_make_snippet(ESTDOC *<var>doc</var>, const CBLIST *<var>words</var>, int <var>wwidth</var>, int <var>hwidth</var>, int <var>awidth</var>);</kbd></dt>
<dd>`doc' specifies a document object.  `word' specifies a list object of words to be highlight.  `wwitdh' specifies whole width of the result.  `hwitdh' specifies width of strings picked up from the beginning of the text.  `awitdh' specifies width of strings picked up around each highlighted word.  The return value is a snippet string of the body text of a document object.  There are tab separated values.  Each line is a string to be shown.  Though most lines have only one field, some lines have two fields.  If the second field exists, the first field is to be shown with highlighted, and the second field means its normalized form.  Because the region of the return value is allocated with the `malloc' call, it should be released with the `free' call if it is no longer in use.</dd>
</dl>

<p>The function `est_doc_scan_words' is used in order to check whether the text of a document object includes every specified words.</p>

<dl>
<dt><kbd>int est_doc_scan_words(ESTDOC *<var>doc</var>, const CBLIST *<var>words</var>);</kbd></dt>
<dd>`doc' specifies a document object.  `word' specifies a list object of words to be checked.  The return value is true if every specified words is found, else it is false.</dd>
</dl>

<hr />

<h2 id="estcond">API for Search Conditions</h2>

<p>The API for search conditions aims to specify search conditions given to the index.</p>

<h3>Description</h3>

<p>The type of the structure `ESTCOND' is for abstraction of search conditions.  A unit of search conditions is composed of one search phrase, some attribute expressions, and one order expression.  No entitiy of `ESTCOND' is accessed directly, but it is accessed by the pointer.  The term of "condition object" means the pointer and its referent.  A condition object is created by the function `est_cond_new' and destroyed by `est_cond_delete'.  Every created condition object should be destroyed.</p>

<p>Condition objects are used as a parameter to search for documents registered in the database so that a list of IDs of corresponding documents are returned.  See <a href="manual-en.html#searchcond">the manual</a> for the formats of expressions.  The encoding of conditional expressions should be UTF-8.</p>

<p>The following is a typical use case of condition object.</p>

<pre>ESTCOND *cond;

/* create a condition object */
cond = est_cond_new();

/* set the search phrase */
est_cond_set_phrase(cond, "check AND out");

/* set the attribute expression */
est_cond_add_attr(cond, "@uri ISTREW .txt");

  /* search the database here */

/* destroy the object */
est_cond_delete(cond);
</pre>

<h3>API</h3>

<p>The function `est_cond_new' is used in order to create a condition object.</p>

<dl>
<dt><kbd>ESTCOND *est_cond_new(void);</kbd></dt>
<dd>The return value is an object of search conditions.</dd>
</dl>

<p>The function `est_cond_delete' is used in order to destroy a condition object.</p>

<dl>
<dt><kbd>void est_cond_delete(ESTCOND *<var>cond</var>);</kbd></dt>
<dd>`cond' specifies a condition object.</dd>
</dl>

<p>The function `est_cond_set_phrase' is used in order to set the search phrase to a condition object.</p>

<dl>
<dt><kbd>void est_cond_set_phrase(ESTCOND *<var>cond</var>, const char *<var>phrase</var>);</kbd></dt>
<dd>`cond' specifies a condition object.  `phrase' specifies a search phrase.</dd>
</dl>

<p>The function `est_cond_add_attr' is used in order to add an expression for an attribute to a condition object.</p>

<dl>
<dt><kbd>void est_cond_add_attr(ESTCOND *<var>cond</var>, const char *<var>expr</var>);</kbd></dt>
<dd>`cond' specifies a condition object.  `expr' specifies an expression for an attribute.</dd>
</dl>

<p>The function `est_cond_set_order' is used in order to set the order of a condition object.</p>

<dl>
<dt><kbd>void est_cond_set_order(ESTCOND *<var>cond</var>, const char *<var>expr</var>);</kbd></dt>
<dd>`cond' specifies a condition object.  `expr' specifies an expression for the order.  By default, the order is by score descending.</dd>
</dl>

<p>The function `est_cond_set_max' is used in order to set the maximum number of retrieval of a condition object.</p>

<dl>
<dt><kbd>void est_cond_set_max(ESTCOND *<var>cond</var>, int <var>max</var>);</kbd></dt>
<dd>`cond' specifies a condition object.  `max' specifies the maximum number of retrieval.  By default, the number of retrieval is not limited.</dd>
</dl>

<p>The function `est_cond_set_options' is used in order to set options of retrieval of a condition object.</p>

<dl>
<dt><kbd>void est_cond_set_options(ESTCOND *<var>cond</var>, int <var>options</var>);</kbd></dt>
<dd>`cond' specifies a condition object.  `options' specifies options: `ESTCONDSURE' specifies that it checks every N-gram key, `ESTCONDUSU', which is the default, specifies that it checks N-gram keys with skipping one key, `ESTCONDFAST' skips two keys, `ESTCONDAGIT' skips three keys, `ESTCONDNOIDF' specifies not to perform TF-IDF tuning, `ESTCONDSIMPLE' specifies to use simplefied phrase.  Each option can be specified at the same time by bitwise or.  If keys are skipped, though search speed is improved, the relevance ratio grows less.</dd>
</dl>

<hr />

<h2 id="estdb">API for Database</h2>

<p>The API for database aims to handle the database of the index.</p>

<h3>Description</h3>

<p>The type of the structure `ESTDB' is for abstraction of access methods to database.  A database has inverted index, document data, and meta data.  One of writer or reader is selected when the connection is established.  No entitiy of `ESTDB' is accessed directly, but it is accessed by the pointer.  The term of "database object" means the pointer and its referent.  A database object is created by the function `est_db_open' and destroyed by `est_db_close'.  Every created database object should be destroyed.</p>

<p>Errors with some operations are informed to by the function `est_db_error'.  The meaning of each error code can be gotten as a string by the function `est_err_msg'.</p>

<p>The following is a typical use case of database object.</p>

<pre>
ESTDB *db
int ecode;

/* create a database object as a write */
if(!(db = est_db_open("casket", ESTDBWRITER | ESTDBCREAT, &amp;ecode))){
  /* if failure, return after displaying the error message */
  fprintf(stderr, "error: %s\n", est_err_msg(ecode));
  return -1;
}

  /* register documents or search for documents here */

/* destroy the object */
if(!est_db_close(db, &amp;ecode)){
  /* if failure, return after displaying the error message */
  fprintf(stderr, "error: %s\n", est_err_msg(ecode));
  return -1;
}
</pre>

<h3>API</h3>

<p>The following constant are defined for error codes.</p>

<ul>
<li><kbd>ESTENOERR</kbd> : no error.</li>
<li><kbd>ESTEINVAL</kbd> : invalid argument.</li>
<li><kbd>ESTEACCES</kbd> : access forbidden.</li>
<li><kbd>ESTELOCK</kbd> : lock failure.</li>
<li><kbd>ESTEDB</kbd> : database problem.</li>
<li><kbd>ESTEIO</kbd> : I/O problem.</li>
<li><kbd>ESTENOITEM</kbd> : no item.</li>
<li><kbd>ESTEMISC</kbd> : miscellaneous.</li>
</ul>

<p>The function `est_err_msg' is used in order to get the string of an error code.</p>

<dl>
<dt><kbd>const char *est_err_msg(int <var>ecode</var>);</kbd></dt>
<dd>`ecode' specifies an error code.  The return value is the string of the error code.</dd>
</dl>

<p>The function `est_db_open' is used in order to open a database.</p>

<dl>
<dt><kbd>ESTDB *est_db_open(const char *<var>name</var>, int <var>omode</var>, int *<var>ecp</var>);</kbd></dt>
<dd>`name' specifies the name of a database directory.  `mode' specifies open modes: `ESTDBWRITER' as a writer, `ESTDBREADER' as a reader.  If the mode is `ESTDBWRITER', the following may be added by bitwise or: `ESTDBCREAT', which means it creates a new database if not exist, `ESTDBTRUNC', which means it creates a new database regardless if one exists.  Both of `ESTDBREADER' and  `ESTDBWRITER' can be added to by bitwise or: `ESTDBNOLCK', which means it opens a database file without file locking, or `ESTDBLCKNB', which means locking is performed without blocking.  If `ESTDBNOLCK' is used, the application is responsible for exclusion control.  `ESTDBCREAT' can be added to by bitwise or: `ESTDBPERFNG', which means N-gram analysis is performed against Europian text also.  `ecp' specifies the pointer to a variable to which the error code is assigned.  The return value is a database object of the database or `NULL' if failure.</dd>
</dl>

<p>The function `est_db_close' is used in order to close a database.</p>

<dl>
<dt><kbd>int est_db_close(ESTDB *<var>db</var>, int *<var>ecp</var>);</kbd></dt>
<dd>`db' specifies a database object.  `ecp' specifies the pointer to a variable to which the error code is assigned.  The return value is true if success, else it is false.</dd>
</dl>

<p>The function `est_db_error' is used in order to get the last happended error code of a database.</p>

<dl>
<dt><kbd>int est_db_error(ESTDB *<var>db</var>);</kbd></dt>
<dd>`db' specifies a database object.  The return value is the last happended error code of the database.</dd>
</dl>

<p>The function `est_db_fatal' is used in order to check whether a database has a fatal error.</p>

<dl>
<dt><kbd>int est_db_fatal(ESTDB *<var>db</var>);</kbd></dt>
<dd>`db' specifies a database object.  The return value is true if the database has fatal erroor, else it is false.</dd>
</dl>

<p>The function `est_db_flush' is used in order to flush index words in the cache of a database.</p>

<dl>
<dt><kbd>int est_db_flush(ESTDB *<var>db</var>, int <var>max</var>);</kbd></dt>
<dd>`db' specifies a database object connected as a writer.  `max' specifies the maximum number of words to be flushed.  If it not more than zero, all words are flushed.  The return value is true if success, else it is false.</dd>
</dl>

<p>The function `est_db_sync' is used in order to synchronize updating contents of a database.</p>

<dl>
<dt><kbd>int est_db_sync(ESTDB *<var>db</var>);</kbd></dt>
<dd>`db' specifies a database object connected as a writer.  The return value is true if success, else it is false.</dd>
</dl>

<p>The function `est_db_optimize' is used in order to optimize a database.</p>

<dl>
<dt><kbd>int est_db_optimize(ESTDB *<var>db</var>, int <var>options</var>);</kbd></dt>
<dd>`db' specifies a database object connected as a writer.  `options' specifies options: `ESTOPTNOPURGE' to omit purging dispensable region of deleted documents, `ESTOPTNODBOPT' to omit optimizization of the database files.  The two can be specified at the same time by bitwise or.  The return value is true if success, else it is false.</dd>
</dl>

<p>The function `est_db_put_doc' is used in order to add a document to a database.</p>

<dl>
<dt><kbd>int est_db_put_doc(ESTDB *<var>db</var>, ESTDOC *<var>doc</var>, int <var>options</var>);</kbd></dt>
<dd>`db' specifies a database object connected as a writer.  `doc' specifies a document object.  The document object should have the URI attribute.  `options' specifies options: `ESTPDCLEAN' to clean up dispensable regions of the overwritten document.  The return value is true if success, else it is false.  If the URI attribute is same with an existing document in the database, the existing one is deleted.</dd>
</dl>

<p>The function `est_db_out_doc' is used in order to remove a document from a database.</p>

<dl>
<dt><kbd>int est_db_out_doc(ESTDB *<var>db</var>, int <var>id</var>, int <var>options</var>);</kbd></dt>
<dd>`db' specifies a database object connected as a writer.  `id' specifies the ID number of a registered document.  `options' specifies options: `ESTODCLEAN' to clean up dispensable regions of the deleted document.  The return value is true if success, else it is false.</dd>
</dl>

<p>The function `est_db_get_doc' is used in order to retrieve a document in a database.</p>

<dl>
<dt><kbd>ESTDOC *est_db_get_doc(ESTDB *<var>db</var>, int <var>id</var>, int <var>options</var>);</kbd></dt>
<dd>`db' specifies a database object.  `id' specifies the ID number of a registered document.  `options' specifies options: `ESTGDNOATTR' to ignore attributes, `ESTGDNOTEXT' to ignore the body text.  The two can be specified at the same time by bitwise or.  The return value is a document object.  On error, `NULL' is returned.</dd>
</dl>

<p>The function `est_db_get_doc_attr' is used in order to retrieve the value of an attribute of a document in a database.</p>

<dl>
<dt><kbd>char *est_db_get_doc_attr(ESTDB *<var>db</var>, int <var>id</var>, const char *<var>name</var>);</kbd></dt>
<dd>`db' specifies a database object.  `id' specifies the ID number of a registered document.  `name' specifies the name of an attribute.  The return value is the value of the attribute or `NULL' if it does not exist.  Because the region of the return value is allocated with the `malloc' call, it should be released with the `free' call if it is no longer in use.</dd>
</dl>

<p>The function `est_db_uri_to_id' is used in order to get the ID of a document spacified by URI.</p>

<dl>
<dt><kbd>int est_db_uri_to_id(ESTDB *<var>db</var>, const char *<var>uri</var>);</kbd></dt>
<dd>`db' specifies a database object.  `uri' specifies the URI of a registered document.  The return value is the ID of the document.  On error, -1 is returned.</dd>
</dl>

<p>The function `est_db_etch_doc' to extract keywords of a document object.</p>

<dl>
<dt><kbd>CBMAP *est_db_etch_doc(ESTDB *<var>db</var>, ESTDOC *<var>doc</var>, int <var>max</var>);</kbd></dt>
<dd>`db' specifies a database object for TF-IDF tuning.  If it is `NULL', it is not used.  `doc' specifies a document object.  `max' specifies the maximum number of keywords to be extracted.  The return value is a new map object of keywords and their scores in decimal string.  Because the object of the return value is opened with the function `cbmapopen', it should be closed with the function `cbmapclose' if it is no longer in use.</dd>
</dl>

<p>The function `est_db_iter_init' is used in order to initialize the iterator of a database.</p>

<dl>
<dt><kbd>int est_db_iter_init(ESTDB *<var>db</var>);</kbd></dt>
<dd>`db' specifies a database object.  The return value is true if success, else it is false.</dd>
</dl>

<p>The function `est_db_iter_next' is used in order to get the next ID of the iterator of a database.</p>

<dl>
<dt><kbd>int est_db_iter_next(ESTDB *<var>db</var>);</kbd></dt>
<dd>`db' specifies a database object.  The return value is the next ID.  If there is no more document, 0 is returned.  On error, -1 is returned.</dd>
</dl>

<p>The function `est_db_name' is used in order to get the name of a database.</p>

<dl>
<dt><kbd>const char *est_db_name(ESTDB *<var>db</var>);</kbd></dt>
<dd>`db' specifies a database object.  The return value is the name of the database.  The life duration of the returned string is synchronous with the one of the database object.</dd>
</dl>

<p>The function `est_db_doc_num' is used in order to get the number of documents in a database.</p>

<dl>
<dt><kbd>int est_db_doc_num(ESTDB *<var>db</var>);</kbd></dt>
<dd>`db' specifies a database object.  The return value is the number of documents in the database.</dd>
</dl>

<p>The function `est_db_word_num' is used in order to get the number of unique words in a database.</p>

<dl>
<dt><kbd>int est_db_word_num(ESTDB *<var>db</var>);</kbd></dt>
<dd>`db' specifies a database object.  The return value is the number of unique words in the database.</dd>
</dl>

<p>The function `est_db_size' is used in order to get the size of a database.</p>

<dl>
<dt><kbd>double est_db_size(ESTDB *<var>db</var>);</kbd></dt>
<dd>`db' specifies a database object.  The return value is the size of the database.</dd>
</dl>

<p>The function `est_db_search' is used in order to search documents corresponding a condition for a database.</p>

<dl>
<dt><kbd>int *est_db_search(ESTDB *<var>db</var>, ESTCOND *<var>cond</var>, int *<var>nump</var>, CBMAP *<var>hints</var>);</kbd></dt>
<dd>`db' specifies a database object.  `cond' specifies a condition object.  `nump' specifies the pointer to a variable to which the number of elements in the result is assigned.  `hints' specifies a map object into which the number of documents corresponding to each word is stored.  If a word is in a negative condition, the number is negative.  The element whose key is an empty string specifies the number of whole result.  If it is `NULL', it is not used.  The return value is an array whose elements are ID numbers of corresponding documents.  This function does never fail.  Even if no document corresponds or an error occurs, an empty array is returned.  Because the region of the return value is allocated with the `malloc' call, it should be released with the `free' call if it is no longer in use.</dd>
</dl>

<p>The function `est_db_set_cache_size' is used in order to set the maximum size of the cache memory of a database.</p>

<dl>
<dt><kbd>void est_db_set_cache_size(ESTDB *<var>db</var>, size_t <var>size</var>, int <var>anum</var>, int <var>tnum</var>);</kbd></dt>
<dd>`db' specifies a database object.  `size' specifies the maximum size of the index cache.  By default, it is 64MB.  If it is not more than 0, the current size is not changed.  `anum' specifies the maximum number of cached records for document attributes.  By default, it is 8192.  If it is not more than 0, the current size is not changed.  `tnum' specifies the maximum number of cached records for document texts.  By default, it is 1024.  If it is not more than 0, the current size is not changed.</dd>
</dl>

<hr />

<h2 id="gatherer">Example of Gatherer</h2>

<p>The following is the simplest implementation of a gatherer.</p>

<pre>#include &lt;estraier.h&gt;
#include &lt;cabin.h&gt;
#include &lt;stdlib.h&gt;
#include &lt;stdio.h&gt;

int main(int argc, char **argv){
  ESTDB *db;
  ESTDOC *doc;
  int ecode;

  /* open the database */
  if(!(db = est_db_open("casket", ESTDBWRITER | ESTDBCREAT, &amp;ecode))){
    fprintf(stderr, "error: %s\n", est_err_msg(ecode));
    return 1;
  }

  /* create a document object */
  doc = est_doc_new();

  /* add attributes to the document object */
  est_doc_add_attr(doc, "@uri", "http://estraier.gov/example.txt");
  est_doc_add_attr(doc, "@title", "Over the Rainbow");

  /* add the body text to the document object */
  est_doc_add_text(doc, "Somewhere over the rainbow.  Way up high.");
  est_doc_add_text(doc, "There's a land that I heard of once in a lullaby.");

  /* register the document object to the database */
  if(!est_db_put_doc(db, doc, ESTPDCLEAN))
    fprintf(stderr, "error: %s\n", est_err_msg(est_db_error(db)));

  /* destroy the document object */
  est_doc_delete(doc);

  /* close the database */
  if(!est_db_close(db, &amp;ecode)){
    fprintf(stderr, "error: %s\n", est_err_msg(ecode));
    return 1;
  }

  return 0;
}
</pre>

<hr />

<h2 id="searcher">Example of Searcher</h2>

<p>The following is the simplest implementation of a searcher.</p>

<pre>#include &lt;estraier.h&gt;
#include &lt;cabin.h&gt;
#include &lt;stdlib.h&gt;
#include &lt;stdio.h&gt;

int main(int argc, char **argv){
  ESTDB *db;
  ESTCOND *cond;
  ESTDOC *doc;
  const CBLIST *texts;
  int ecode, *result, resnum, i, j;
  const char *value;

  /* open the database */
  if(!(db = est_db_open("casket", ESTDBREADER, &amp;ecode))){
    fprintf(stderr, "error: %s\n", est_err_msg(ecode));
    return 1;
  }

  /* create a search condition object */
  cond = est_cond_new();

  /* set the search phrase to the search condition object */
  est_cond_set_phrase(cond, "rainbow AND lullaby");

  /* get the result of search */
  result = est_db_search(db, cond, &amp;resnum, NULL);

  /* for each document in the result */
  for(i = 0; i &lt; resnum; i++){

    /* retrieve the document object */
    if(!(doc = est_db_get_doc(db, result[i], 0))) continue;

    /* display attributes */
    if((value = est_doc_attr(doc, "@uri")) != NULL)
      printf("URI: %s\n", value);
    if((value = est_doc_attr(doc, "@title")) != NULL)
      printf("Title: %s\n", value);

    /* display the body text */
    texts = est_doc_texts(doc);
    for(j = 0; j &lt; cblistnum(texts); j++){
      value = cblistval(texts, j, NULL);
      printf("%s\n", value);
    }

    /* destloy the document object */
    est_doc_delete(doc);

  }

  /* free the result of search */
  free(result);

  /* destroy the search condition object */
  est_cond_delete(cond);

  /* close the database */
  if(!est_db_close(db, &amp;ecode)){
    fprintf(stderr, "error: %s\n", est_err_msg(ecode));
    return 1;
  }

  return 0;
}
</pre>

<hr />

<h2 id="paralleling">Paralleling</h2>

<p>Databases of Hyper Estraier are protected by file locking.  While a writer is connected to a database, neither readers nor writers can be connected.  While a reader is connected to a database, other readers can be connect, but writers can not.</p>

<p>If you use multi thread, it is suggested to use the MT-safe API of Hyper Estraier.  It is a wrapper to make the core API thread-safe.  As the MT-safe API provides the same functions as with the core API, the following is different.</p>

<ul>
<li>Include not only `estraier.h' but also `estmtdb.h'.</li>
<li>Use pointers to `ESTMTDB' instead of `ESTDB' as database objects.</li>
<li>The names of functions begin with "est_mtdb_" instead of "est_db_".</li>
</ul>

<p>If QDBM was built with `--enable-pthread', mutex protection is performed for each connection, not in global.  So, it is recommended when you use the MT-safe API.</p>

<hr />

</body>

</html>

<!-- END OF FILE -->