<?xml version="1.0" encoding="ascii"?> <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "DTD/xhtml1-transitional.dtd"> <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"> <head> <title>Bio.GenBank.utils</title> <link rel="stylesheet" href="epydoc.css" type="text/css" /> <script type="text/javascript" src="epydoc.js"></script> </head> <body bgcolor="white" text="black" link="blue" vlink="#204080" alink="#204080"> <!-- ==================== NAVIGATION BAR ==================== --> <table class="navbar" border="0" width="100%" cellpadding="0" bgcolor="#a0c0ff" cellspacing="0"> <tr valign="middle"> <!-- Tree link --> <th> <a href="module-tree.html">Trees</a> </th> <!-- Index link --> <th> <a href="identifier-index.html">Indices</a> </th> <!-- Help link --> <th> <a href="help.html">Help</a> </th> <th class="navbar" width="100%"></th> </tr> </table> <table width="100%" cellpadding="0" cellspacing="0"> <tr valign="top"> <td width="100%"> <span class="breadcrumbs"> <a href="Bio-module.html">Package Bio</a> :: <a href="Bio.GenBank-module.html">Package GenBank</a> :: Module utils </span> </td> <td> <table cellpadding="0" cellspacing="0"> <!-- hide/show private --> <tr><td align="right"><span class="options">[<a href="javascript:void(0);" class="privatelink" onclick="toggle_private();">hide private</a>]</span></td></tr> <tr><td align="right"><span class="options" >[<a href="frames.html" target="_top">frames</a >] | <a href="Bio.GenBank.utils-pysrc.html" target="_top">no frames</a>]</span></td></tr> </table> </td> </tr> </table> <h1 class="epydoc">Source Code for <a href="Bio.GenBank.utils-module.html">Module Bio.GenBank.utils</a></h1> <pre class="py-src"> <a name="L1"></a><tt class="py-lineno"> 1</tt> <tt class="py-line"><tt class="py-docstring">"""Useful utilities for helping in parsing GenBank files.</tt> </tt> <a name="L2"></a><tt class="py-lineno"> 2</tt> <tt class="py-line"><tt class="py-docstring">"""</tt> </tt> <a name="L3"></a><tt class="py-lineno"> 3</tt> <tt class="py-line"><tt class="py-comment"># standard library</tt> </tt> <a name="L4"></a><tt class="py-lineno"> 4</tt> <tt class="py-line"><tt class="py-comment"></tt><tt class="py-keyword">import</tt> <tt class="py-name">string</tt> </tt> <a name="L5"></a><tt class="py-lineno"> 5</tt> <tt class="py-line"> </tt> <a name="FeatureValueCleaner"></a><div id="FeatureValueCleaner-def"><a name="L6"></a><tt class="py-lineno"> 6</tt> <a class="py-toggle" href="#" id="FeatureValueCleaner-toggle" onclick="return toggle('FeatureValueCleaner');">-</a><tt class="py-line"><tt class="py-keyword">class</tt> <a class="py-def-name" href="Bio.GenBank.utils.FeatureValueCleaner-class.html">FeatureValueCleaner</a><tt class="py-op">:</tt> </tt> </div><div id="FeatureValueCleaner-collapsed" style="display:none;" pad="++" indent="++++"></div><div id="FeatureValueCleaner-expanded"><a name="L7"></a><tt class="py-lineno"> 7</tt> <tt class="py-line"> <tt class="py-docstring">"""Provide specialized capabilities for cleaning up values in features.</tt> </tt> <a name="L8"></a><tt class="py-lineno"> 8</tt> <tt class="py-line"><tt class="py-docstring"></tt> </tt> <a name="L9"></a><tt class="py-lineno"> 9</tt> <tt class="py-line"><tt class="py-docstring"> This class is designed to provide a mechanism to clean up and process</tt> </tt> <a name="L10"></a><tt class="py-lineno">10</tt> <tt class="py-line"><tt class="py-docstring"> values in the key/value pairs of GenBank features. This is useful </tt> </tt> <a name="L11"></a><tt class="py-lineno">11</tt> <tt class="py-line"><tt class="py-docstring"> because in cases like:</tt> </tt> <a name="L12"></a><tt class="py-lineno">12</tt> <tt class="py-line"><tt class="py-docstring"> </tt> </tt> <a name="L13"></a><tt class="py-lineno">13</tt> <tt class="py-line"><tt class="py-docstring"> /translation="MED</tt> </tt> <a name="L14"></a><tt class="py-lineno">14</tt> <tt class="py-line"><tt class="py-docstring"> YDPWNLRFQSKYKSRDA"</tt> </tt> <a name="L15"></a><tt class="py-lineno">15</tt> <tt class="py-line"><tt class="py-docstring"></tt> </tt> <a name="L16"></a><tt class="py-lineno">16</tt> <tt class="py-line"><tt class="py-docstring"> you'll end up with a value with \012s and spaces in it like:</tt> </tt> <a name="L17"></a><tt class="py-lineno">17</tt> <tt class="py-line"><tt class="py-docstring"> "MED\012 YDPWEL..."</tt> </tt> <a name="L18"></a><tt class="py-lineno">18</tt> <tt class="py-line"><tt class="py-docstring"></tt> </tt> <a name="L19"></a><tt class="py-lineno">19</tt> <tt class="py-line"><tt class="py-docstring"> which you probably don't want. </tt> </tt> <a name="L20"></a><tt class="py-lineno">20</tt> <tt class="py-line"><tt class="py-docstring"> </tt> </tt> <a name="L21"></a><tt class="py-lineno">21</tt> <tt class="py-line"><tt class="py-docstring"> This cleaning needs to be done on a case by case basis since it is</tt> </tt> <a name="L22"></a><tt class="py-lineno">22</tt> <tt class="py-line"><tt class="py-docstring"> impossible to interpret whether you should be concatenating everything</tt> </tt> <a name="L23"></a><tt class="py-lineno">23</tt> <tt class="py-line"><tt class="py-docstring"> (as in translations), or combining things with spaces (as might be</tt> </tt> <a name="L24"></a><tt class="py-lineno">24</tt> <tt class="py-line"><tt class="py-docstring"> the case with /notes).</tt> </tt> <a name="L25"></a><tt class="py-lineno">25</tt> <tt class="py-line"><tt class="py-docstring"> """</tt> </tt> <a name="L26"></a><tt class="py-lineno">26</tt> <tt class="py-line"> <tt id="link-0" class="py-name" targets="Variable Bio.GenBank.utils.FeatureValueCleaner.keys_to_process=Bio.GenBank.utils.FeatureValueCleaner-class.html#keys_to_process"><a title="Bio.GenBank.utils.FeatureValueCleaner.keys_to_process" class="py-name" href="#" onclick="return doclink('link-0', 'keys_to_process', 'link-0');">keys_to_process</a></tt> <tt class="py-op">=</tt> <tt class="py-op">[</tt><tt class="py-string">"translation"</tt><tt class="py-op">]</tt> </tt> <a name="FeatureValueCleaner.__init__"></a><div id="FeatureValueCleaner.__init__-def"><a name="L27"></a><tt class="py-lineno">27</tt> <a class="py-toggle" href="#" id="FeatureValueCleaner.__init__-toggle" onclick="return toggle('FeatureValueCleaner.__init__');">-</a><tt class="py-line"> <tt class="py-keyword">def</tt> <a class="py-def-name" href="Bio.GenBank.utils.FeatureValueCleaner-class.html#__init__">__init__</a><tt class="py-op">(</tt><tt class="py-param">self</tt><tt class="py-op">,</tt> <tt class="py-param">to_process</tt> <tt class="py-op">=</tt> <tt id="link-1" class="py-name"><a title="Bio.GenBank.utils.FeatureValueCleaner.keys_to_process" class="py-name" href="#" onclick="return doclink('link-1', 'keys_to_process', 'link-0');">keys_to_process</a></tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt> </div><div id="FeatureValueCleaner.__init__-collapsed" style="display:none;" pad="++" indent="++++++++"></div><div id="FeatureValueCleaner.__init__-expanded"><a name="L28"></a><tt class="py-lineno">28</tt> <tt class="py-line"> <tt class="py-docstring">"""Initialize with the keys we should deal with.</tt> </tt> <a name="L29"></a><tt class="py-lineno">29</tt> <tt class="py-line"><tt class="py-docstring"> """</tt> </tt> <a name="L30"></a><tt class="py-lineno">30</tt> <tt class="py-line"> <tt class="py-name">self</tt><tt class="py-op">.</tt><tt class="py-name">_to_process</tt> <tt class="py-op">=</tt> <tt class="py-name">to_process</tt> </tt> </div><a name="L31"></a><tt class="py-lineno">31</tt> <tt class="py-line"> </tt> <a name="FeatureValueCleaner.clean_value"></a><div id="FeatureValueCleaner.clean_value-def"><a name="L32"></a><tt class="py-lineno">32</tt> <a class="py-toggle" href="#" id="FeatureValueCleaner.clean_value-toggle" onclick="return toggle('FeatureValueCleaner.clean_value');">-</a><tt class="py-line"> <tt class="py-keyword">def</tt> <a class="py-def-name" href="Bio.GenBank.utils.FeatureValueCleaner-class.html#clean_value">clean_value</a><tt class="py-op">(</tt><tt class="py-param">self</tt><tt class="py-op">,</tt> <tt class="py-param">key_name</tt><tt class="py-op">,</tt> <tt class="py-param">value</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt> </div><div id="FeatureValueCleaner.clean_value-collapsed" style="display:none;" pad="++" indent="++++++++"></div><div id="FeatureValueCleaner.clean_value-expanded"><a name="L33"></a><tt class="py-lineno">33</tt> <tt class="py-line"> <tt class="py-docstring">"""Clean the specified value and return it.</tt> </tt> <a name="L34"></a><tt class="py-lineno">34</tt> <tt class="py-line"><tt class="py-docstring"></tt> </tt> <a name="L35"></a><tt class="py-lineno">35</tt> <tt class="py-line"><tt class="py-docstring"> If the value is not specified to be dealt with, the original value</tt> </tt> <a name="L36"></a><tt class="py-lineno">36</tt> <tt class="py-line"><tt class="py-docstring"> will be returned.</tt> </tt> <a name="L37"></a><tt class="py-lineno">37</tt> <tt class="py-line"><tt class="py-docstring"> """</tt> </tt> <a name="L38"></a><tt class="py-lineno">38</tt> <tt class="py-line"> <tt class="py-keyword">if</tt> <tt class="py-name">key_name</tt> <tt class="py-keyword">in</tt> <tt class="py-name">self</tt><tt class="py-op">.</tt><tt class="py-name">_to_process</tt><tt class="py-op">:</tt> </tt> <a name="L39"></a><tt class="py-lineno">39</tt> <tt class="py-line"> <tt class="py-keyword">try</tt><tt class="py-op">:</tt> </tt> <a name="L40"></a><tt class="py-lineno">40</tt> <tt class="py-line"> <tt class="py-name">cleaner</tt> <tt class="py-op">=</tt> <tt class="py-name">getattr</tt><tt class="py-op">(</tt><tt class="py-name">self</tt><tt class="py-op">,</tt> <tt class="py-string">"_clean_%s"</tt> <tt class="py-op">%</tt> <tt class="py-name">key_name</tt><tt class="py-op">)</tt> </tt> <a name="L41"></a><tt class="py-lineno">41</tt> <tt class="py-line"> <tt id="link-2" class="py-name" targets="Variable Bio.Translate.value=Bio.Translate-module.html#value"><a title="Bio.Translate.value" class="py-name" href="#" onclick="return doclink('link-2', 'value', 'link-2');">value</a></tt> <tt class="py-op">=</tt> <tt class="py-name">cleaner</tt><tt class="py-op">(</tt><tt id="link-3" class="py-name"><a title="Bio.Translate.value" class="py-name" href="#" onclick="return doclink('link-3', 'value', 'link-2');">value</a></tt><tt class="py-op">)</tt> </tt> <a name="L42"></a><tt class="py-lineno">42</tt> <tt class="py-line"> <tt class="py-keyword">except</tt> <tt class="py-name">AttributeError</tt><tt class="py-op">:</tt> </tt> <a name="L43"></a><tt class="py-lineno">43</tt> <tt class="py-line"> <tt class="py-keyword">raise</tt> <tt class="py-name">AssertionError</tt><tt class="py-op">(</tt><tt class="py-string">"No function to clean key: %s"</tt> </tt> <a name="L44"></a><tt class="py-lineno">44</tt> <tt class="py-line"> <tt class="py-op">%</tt> <tt class="py-name">key_name</tt><tt class="py-op">)</tt> </tt> <a name="L45"></a><tt class="py-lineno">45</tt> <tt class="py-line"> <tt class="py-keyword">return</tt> <tt id="link-4" class="py-name"><a title="Bio.Translate.value" class="py-name" href="#" onclick="return doclink('link-4', 'value', 'link-2');">value</a></tt> </tt> </div><a name="L46"></a><tt class="py-lineno">46</tt> <tt class="py-line"> </tt> <a name="FeatureValueCleaner._clean_translation"></a><div id="FeatureValueCleaner._clean_translation-def"><a name="L47"></a><tt class="py-lineno">47</tt> <a class="py-toggle" href="#" id="FeatureValueCleaner._clean_translation-toggle" onclick="return toggle('FeatureValueCleaner._clean_translation');">-</a><tt class="py-line"> <tt class="py-keyword">def</tt> <a class="py-def-name" href="Bio.GenBank.utils.FeatureValueCleaner-class.html#_clean_translation">_clean_translation</a><tt class="py-op">(</tt><tt class="py-param">self</tt><tt class="py-op">,</tt> <tt class="py-param">value</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt> </div><div id="FeatureValueCleaner._clean_translation-collapsed" style="display:none;" pad="++" indent="++++++++"></div><div id="FeatureValueCleaner._clean_translation-expanded"><a name="L48"></a><tt class="py-lineno">48</tt> <tt class="py-line"> <tt class="py-docstring">"""Concatenate a translation value to one long protein string.</tt> </tt> <a name="L49"></a><tt class="py-lineno">49</tt> <tt class="py-line"><tt class="py-docstring"> """</tt> </tt> <a name="L50"></a><tt class="py-lineno">50</tt> <tt class="py-line"> <tt class="py-name">translation_parts</tt> <tt class="py-op">=</tt> <tt id="link-5" class="py-name"><a title="Bio.Translate.value" class="py-name" href="#" onclick="return doclink('link-5', 'value', 'link-2');">value</a></tt><tt class="py-op">.</tt><tt id="link-6" class="py-name" targets="Method Bio.Nexus.Trees.Tree.split()=Bio.Nexus.Trees.Tree-class.html#split,Method Bio.Restriction.Restriction.RestrictionBatch.split()=Bio.Restriction.Restriction.RestrictionBatch-class.html#split"><a title="Bio.Nexus.Trees.Tree.split Bio.Restriction.Restriction.RestrictionBatch.split" class="py-name" href="#" onclick="return doclink('link-6', 'split', 'link-6');">split</a></tt><tt class="py-op">(</tt><tt class="py-op">)</tt> </tt> <a name="L51"></a><tt class="py-lineno">51</tt> <tt class="py-line"> <tt class="py-keyword">return</tt> <tt class="py-name">string</tt><tt class="py-op">.</tt><tt class="py-name">join</tt><tt class="py-op">(</tt><tt class="py-name">translation_parts</tt><tt class="py-op">,</tt> <tt class="py-string">''</tt><tt class="py-op">)</tt> </tt> </div></div><a name="L52"></a><tt class="py-lineno">52</tt> <tt class="py-line"> </tt><script type="text/javascript"> <!-- expandto(location.href); // --> </script> </pre> <br /> <!-- ==================== NAVIGATION BAR ==================== --> <table class="navbar" border="0" width="100%" cellpadding="0" bgcolor="#a0c0ff" cellspacing="0"> <tr valign="middle"> <!-- Tree link --> <th> <a href="module-tree.html">Trees</a> </th> <!-- Index link --> <th> <a href="identifier-index.html">Indices</a> </th> <!-- Help link --> <th> <a href="help.html">Help</a> </th> <th class="navbar" width="100%"></th> </tr> </table> <table border="0" cellpadding="0" cellspacing="0" width="100%%"> <tr> <td align="left" class="footer"> Generated by Epydoc 3.0.1 on Mon Sep 15 09:26:48 2008 </td> <td align="right" class="footer"> <a target="mainFrame" href="http://epydoc.sourceforge.net" >http://epydoc.sourceforge.net</a> </td> </tr> </table> <script type="text/javascript"> <!-- // Private objects are initially displayed (because if // javascript is turned off then we want them to be // visible); but by default, we want to hide them. So hide // them unless we have a cookie that says to show them. checkCookie(); // --> </script> </body> </html>