diff --git a/src/doc/user/usermanual.html b/src/doc/user/usermanual.html index 78a7b56c..29c8d24e 100644 --- a/src/doc/user/usermanual.html +++ b/src/doc/user/usermanual.html @@ -3,7 +3,7 @@ + "HTML Tidy for HTML5 for Linux version 5.2.0"> Recoll user manual @@ -1135,8 +1135,8 @@ alink="#0000FF"> different areas of the file system to different indexes. For example, if you were to issue the following command:

- 
recoll -c ~/.indexes-email
+ 
+              recoll -c ~/.indexes-email

Then Recoll would use configuration files stored in ~/.indexes-email/ and, (unless @@ -3874,8 +3874,8 @@ fs.inotify.max_user_watches=32768 that every user does not have to do it. The variable should define a colon-separated list of index directories, ie:

- 
export RECOLL_EXTRA_DBS=/some/place/xapiandb:/some/other/db
+ 
+          export RECOLL_EXTRA_DBS=/some/place/xapiandb:/some/other/db

Another environment variable, RECOLL_ACTIVE_EXTRA_DBS allows adding to the active list of indexes. This variable was suggested @@ -4677,8 +4677,8 @@ fs.inotify.max_user_watches=32768 parent folder expansion, usually creating a file manager window on the folder where the container file resides. E.g.:

- 
<a href="F%N">%P</a>
+ 
+              <a href="F%N">%P</a>

A link target defined as R%N|scriptname @@ -4820,8 +4820,8 @@ fs.inotify.max_user_watches=32768 javascript program to the documents, like the following example, which would initiate a search by double-clicking any term:

- 
<script language="JavaScript">
+          
+          <script language="JavaScript">
         function recollsearch() {
         var t = document.getSelection();
         window.location.href = 'recoll://search/query?qtp=a&p=0&q=' +
@@ -5115,7 +5115,17 @@ text/html       [file:///Users/uncrypted-dockes/projets/bateaux/ilur/factEtCie/r
             
  • 
               
    ext specifies the
               file name extension (Ex: ext:html)
    
+              "literal">ext:html).
    
+            
    • 
+            
  • 
+              
    rclmd5 the MD5
+              checksum for the document. This is used for
+              displaying the duplicates of a search result (when
+              querying with the option to collapse duplicate
+              results). Incidentally, this could be used to find
+              the duplicates of any given file by computing its MD5
+              checksum and executing a query with just the
+              rclmd5 value.
    
             
    • 
           
         
@@ -10055,8 +10065,8 @@ for i in range(nres):
           "filename">.xml extension but should be handled
           specially, which is possible because they are usually all
           located in one place. Example:
    
-          
    [~/.kde/share/apps/okular/docdata]
+          
    +          [~/.kde/share/apps/okular/docdata]
         .xml = application/x-okular-notes
    
           
    The recoll_noindex
           mimemap variable has been
diff --git a/src/doc/user/usermanual.xml b/src/doc/user/usermanual.xml
index 66ccd5cb..fefe4b3f 100644
--- a/src/doc/user/usermanual.xml
+++ b/src/doc/user/usermanual.xml
@@ -3896,27 +3896,36 @@ text/html       [file:///Users/uncrypted-dockes/projets/bateaux/ilur/factEtCie/r
         name for an email attachment. 
 
         containerfilename. This is
-        set for all documents, both top-level and contained
-        sub-documents, and is always the name of the filesystem directory
-        entry which contains the data. The terms from this field can
-        only be matched by an explicit field specification (as opposed
-        to terms from filename which are also indexed
-        as general document content). This avoids getting matches for
-        all the sub-documents when searching for the container file
-        name. 
+            set for all documents, both top-level and contained
+            sub-documents, and is always the name of the filesystem directory
+            entry which contains the data. The terms from this field can
+            only be matched by an explicit field specification (as opposed
+            to terms from filename which are also indexed
+            as general document content). This avoids getting matches for
+            all the sub-documents when searching for the container file
+            name. 
         
         ext specifies the file
-        name extension (Ex: ext:html)
+            name extension
+            (Ex: ext:html).
+
+        rclmd5 the MD5 checksum for the
+            document. This is used for displaying the duplicates of a
+            search result (when querying with the option to collapse
+            duplicate results). Incidentally, this could be used to find
+            the duplicates of any given file by computing its MD5 checksum
+            and executing a query with just the rclmd5
+            value.
         
 
       
 
       &RCL; 1.20 and later have a way to specify aliases for the
-      field names, which will save typing, for example by aliasing
-      filename to fn or
-      containerfilename to
-      cfn. See the
-      section about the fields file.
+        field names, which will save typing, for example by aliasing
+        filename to fn or
+        containerfilename to
+        cfn. See the
+        section about the fields file.
        
 
       The document input handlers used while indexing have the
diff --git a/src/rcldb/rcldb.cpp b/src/rcldb/rcldb.cpp
index 6cedda3c..5a94c2f2 100644
--- a/src/rcldb/rcldb.cpp
+++ b/src/rcldb/rcldb.cpp
@@ -1866,10 +1866,11 @@ bool Db::addOrUpdate(const string &udi, const string &parent_udi, Doc &doc)
             RECORD_APPEND(record, string(cstr_mbreaks), multibreaks.str());
         }
     
-        // If the file's md5 was computed, add value and term. 
-        // The value is optionally used for query result duplicate elimination, 
-        // and the term to find the duplicates.
-        // We don't do this for empty docs.
+        // If the file's md5 was computed, add value and term.  The
+        // value is optionally used for query result duplicate
+        // elimination, and the term to find the duplicates (XM is the
+        // prefix for rclmd5 in fields) We don't do this for empty
+        // docs.
         const string *md5;
         if (doc.peekmeta(Doc::keymd5, &md5) && !md5->empty() &&
             md5->compare(cstr_md5empty)) {
diff --git a/src/rcldb/rcldups.cpp b/src/rcldb/rcldups.cpp
index 1a8e3780..06f5266b 100644
--- a/src/rcldb/rcldups.cpp
+++ b/src/rcldb/rcldups.cpp
@@ -1,4 +1,4 @@
-/* Copyright (C) 2013 J.F.Dockes
+/* Copyright (C) 2013-2020 J.F.Dockes
  *   This program is free software; you can redistribute it and/or modify
  *   it under the terms of the GNU General Public License as published by
  *   the Free Software Foundation; either version 2 of the License, or
@@ -35,36 +35,36 @@ using namespace std;
 namespace Rcl {
 
 /** Retrieve the dups of a given document. The input has to be a query result
-  * because we use the xdocid. We get the md5 from this, then the dups */
+ * because we use the xdocid. We get the md5 from this, then the dups */
 bool Db::docDups(const Doc& idoc, vector& odocs)
 {
     if (m_ndb == 0) {
-    LOGERR("Db::docDups: no db\n" );
-    return false;
+        LOGERR("Db::docDups: no db\n");
+        return false;
     }
     if (idoc.xdocid == 0) {
-    LOGERR("Db::docDups: null xdocid in input doc\n" );
-    return false;
+        LOGERR("Db::docDups: null xdocid in input doc\n");
+        return false;
     }
     // Get the xapian doc
     Xapian::Document xdoc;
     XAPTRY(xdoc = m_ndb->xrdb.get_document(Xapian::docid(idoc.xdocid)), 
-       m_ndb->xrdb, m_reason);
+           m_ndb->xrdb, m_reason);
     if (!m_reason.empty()) {
-    LOGERR("Db::docDups: xapian error: "  << (m_reason) << "\n" );
-    return false;
+        LOGERR("Db::docDups: xapian error: " << m_reason << "\n");
+        return false;
     }
 
     // Get the md5
     string digest;
     XAPTRY(digest = xdoc.get_value(VALUE_MD5), m_ndb->xrdb, m_reason);
     if (!m_reason.empty()) {
-    LOGERR("Db::docDups: xapian error: "  << (m_reason) << "\n" );
-    return false;
+        LOGERR("Db::docDups: xapian error: " << m_reason << "\n");
+        return false;
     }
     if (digest.empty()) {
-    LOGDEB("Db::docDups: doc has no md5\n" );
-    return false;
+        LOGDEB("Db::docDups: doc has no md5\n");
+        return false;
     }
     string md5;
     MD5HexPrint(digest, md5);
@@ -72,45 +72,27 @@ bool Db::docDups(const Doc& idoc, vector& odocs)
     SearchData *sdp = new SearchData();
     std::shared_ptr sd(sdp);
     SearchDataClauseSimple *sdc = 
-    new SearchDataClauseSimple(SCLT_AND, md5, "rclmd5");
+        new SearchDataClauseSimple(SCLT_AND, md5, "rclmd5");
     sdc->addModifier(SearchDataClause::SDCM_CASESENS);
     sdc->addModifier(SearchDataClause::SDCM_DIACSENS);
     sd->addClause(sdc);
     Query query(this);
     query.setCollapseDuplicates(0);
     if (!query.setQuery(sd)) {
-    LOGERR("Db::docDups: setQuery failed\n" );
-    return false;
+        LOGERR("Db::docDups: setQuery failed\n");
+        return false;
     }
     int cnt = query.getResCnt();
     for (int i = 0; i < cnt; i++) {
-    Doc doc;
-    if (!query.getDoc(i, doc)) {
-        LOGERR("Db::docDups: getDoc failed at "  << (i) << " (cnt "  << (cnt) << ")\n" );
-        return false;
-    }
-    odocs.push_back(doc);
+        Doc doc;
+        if (!query.getDoc(i, doc)) {
+            LOGERR("Db::docDups: getDoc failed at " << i << " (cnt " << cnt <<
+                   ")\n");
+            return false;
+        }
+        odocs.push_back(doc);
     }
     return true;
 }
 
-#if 0
-    {
-    vector dups;
-    bool ret;
-    LOGDEB("DOCDUPS\n" );
-    ret = m_db->docDups(doc, dups);
-    if (!ret) {
-        LOGDEB("docDups failed\n" );
-    } else if (dups.size() == 1) {
-        LOGDEB("No dups\n" );
-    } else {
-        for (unsigned int i = 0; i < dups.size(); i++) {
-        LOGDEB("Dup: "  << (dups[i].url) << "\n" );
-        }
-    }
-    }
-#endif
-
 }
-