Added management interface to query words in the lexicon and in the p…

…rocess uncovered a BTreeItems bug, whee!

ZCTextIndex.py

@@ -200,8 +200,9 @@ class PLexicon(Lexicon, Acquisition.Implicit, SimpleItem):
 
     meta_type = 'ZCTextIndex Lexicon'
 
-    manage_options = ({'label':'Overview', 'action':'manage_main'},) + \
-                     SimpleItem.manage_options
+    manage_options = ({'label':'Overview', 'action':'manage_main'},
+                      {'label':'Query', 'action':'queryLexicon'},
+                     ) + SimpleItem.manage_options
 
     def __init__(self, id, title='', *pipeline):
         self.id = str(id)
@@ -213,7 +214,50 @@ def __init__(self, id, title='', *pipeline):
     def getPipelineNames(self):
         """Return list of names of pipeline element classes"""
         return [element.__class__.__name__ for element in self._pipeline]
-
+
+    _queryLexicon = DTMLFile('dtml/queryLexicon', globals())
+
+    def queryLexicon(self, REQUEST, words=None, page=0, rows=20, cols=4):
+        """Lexicon browser/query user interface
+        """
+        if words:
+            wids = []
+            for word in words:
+                wids.extend(self.globToWordIds(word))
+            words = [self.get_word(wid) for wid in wids]
+        else:
+            words = self.words()
+
+        word_count = len(words)
+        rows = max(min(rows, 500),1)
+        cols = max(min(cols, 12), 1)
+        page_count = word_count / (rows * cols) + \
+                     (word_count % (rows * cols) > 0)
+        page = max(min(page, page_count - 1), 0)
+        start = rows * cols * page
+        end = min(rows * cols * (page + 1), word_count)
+
+        if word_count:
+            words = list(words[start:end])
+        else:
+            words = []
+
+        columns = []
+        i = 0
+        while i < len(words):
+            columns.append(words[i:i + rows])
+            i += rows
+
+        return self._queryLexicon(self, REQUEST,
+                                  page=page,
+                                  rows=rows,
+                                  cols=cols,
+                                  start_word=start+1,
+                                  end_word=end,
+                                  word_count=word_count,
+                                  page_count=page_count,
+                                  page_columns=columns)
+
     manage_main = DTMLFile('dtml/manageLexicon', globals())
 
 InitializeClass(PLexicon)

dtml/manageLexicon.dtml

@@ -10,12 +10,12 @@
   <span class="form-label">Input Pipeline Stages</span>
 </p>
 
-<p>
+<p class="form-help">
   Text indexed through this lexicon is processed by the following pipeline 
   stages
 </p>
 
-<ol>
+<ol class="form-help">
   <dtml-in name="getPipelineNames">
     <li>&dtml-sequence-item;</li>
   </dtml-in>

dtml/manageZCTextIndex.dtml

@@ -2,8 +2,12 @@
 <dtml-var manage_tabs>
 
 <p class="form-help">
-
-  There is nothing to manage here. Move along.
-
+  The ZCTextIndex Lexicon in use by this index is: 
+  <em><dtml-var expr="lexicon.getId()"></em>
+</p>
+<p class="form-help">
+  <em>Note:</em> You cannot change the lexicon assigned to a ZCTextIndex.
+  To use another lexicon, delete this index and create a new one that
+  uses the desired lexicon.
 </p>
 <dtml-var manage_page_footer>

dtml/queryLexicon.dtml

@@ -0,0 +1,71 @@
+<dtml-var manage_page_header>
+<dtml-var manage_tabs>
+
+<p class="form-help">
+  Browse the words in the lexicon or enter the word(s) you are interested in
+  below. Globbing characters (*, ?) are supported
+</p>
+
+<dtml-let words_str="' '.join(REQUEST.get('words',[]))">
+  <form action="&dtml-URL;">
+    <p class="form-element">
+      <span class="form-label">Word(s)</span>
+      <input name="words:tokens" size="20"  value="&dtml-words_str;" />
+      <input type="submit" value="Query" />
+
+      <span class="form-label">&nbsp;Output Columns:</span>
+      <input name="cols:int" size="2" value="&dtml-cols;" />
+      <span class="form-label">&nbsp;Rows:</span>
+      <input name="rows:int" size="2" value="&dtml-rows;" />
+    </p>
+  </form>
+  <hr />
+  <form action="&dtml-URL;">
+    <table width="100%"  cellpadding="2" cellspacing="0" border="0">
+
+    <tr class="section-bar">
+      <td><span class="form-label">
+        &dtml-word_count; Words Found<dtml-if word_count>,
+        Displaying &dtml-start_word;-&dtml-end_word;
+        </dtml-if>
+
+        <dtml-if expr="page_count > 0">
+          </span></td>
+          <td align="right"><span class="form-label">
+            Page:
+            <select name="page:int" onchange="this.form.submit()">
+              <dtml-in expr="_.range(page_count)" prefix="page">
+                <option value="&dtml-page_item;"
+                <dtml-if expr="page == page_item">
+                  selected
+                </dtml-if>
+                >
+                  <dtml-var expr="page_item+1">
+                </option>
+              </dtml-in>
+            </select>
+            of &dtml-page_count;
+            <input type="submit" value="Go" />
+            <input type="hidden" name="cols:int" value="&dtml-cols;" />
+            <input type="hidden" name="rows:int" value="&dtml-rows;" />
+            <input type="hidden" name="words:tokens" value="&dtml-words_str;" />
+        </dtml-if>
+        </span></td>
+    </tr>
+    </table>
+  </form>
+</dtml-let>
+
+<dtml-if name="page_columns">
+  <table width="100%" cellpadding="0" cellspacing="10" border="0">
+    <tr>
+    <dtml-in name="page_columns" prefix="column">
+      <td align="left" valign="top">
+        <dtml-var expr="'<br />'.join(column_item)">
+      </td>
+    </dtml-in>
+    </tr>
+  </table>
+</dtml-if>
+
+<dtml-var manage_page_footer

help/Lexicon_Add.stx

@@ -25,14 +25,13 @@ ZCTextIndex Lexicon - Add: Create a new ZCTextIndex Lexicon
               tags. The HTML aware splitter gives best results when all of
               the incoming content to index is HTML.
 
-            - **Stop Words** To conserve space in the vocabulary, and possibly increase
-              performance, you can select a stop word remover which subtracts
-              very common or single letter words from the Lexicon. Bear in
-              mind that you will not be able to search on removed stop words,
-              and they will also be removed from queries passed to search
-              ZCTextIndexes using the Lexicon.
+            - **Stop Words** To conserve space in the vocabulary, and possibly
+              increase performance, you can select a stop word remover which
+              subtracts very common or single letter words from the Lexicon.
+              Bear in mind that you will not be able to search on removed stop
+              words, and they will also be removed from queries passed to
+              search ZCTextIndexes using the Lexicon.
 
-            - **Case Normalizer** The case normalizer removes case information from the words in
-              the  Lexicon. If case-sensitive searching is desires, then omit
-              this element from the pipeline.
-S
+            - **Case Normalizer** The case normalizer removes case information
+              from the words in the  Lexicon. If case-sensitive searching is
+              desires, then omit this element from the pipeline.