Add nearest12 command

Author: kovzol

cli.cpp

@@ -77,6 +77,7 @@ string quitCmd = "quit";
 string helpCmd = "help";
 string statementCmd = "statement";
 string statementCmd2 = "Statement";
+string nearestCmd = "nearest";
 
 string errorNotRecognized
     = "Sorry, the command you entered was not recognized or its syntax is invalid.";
@@ -108,6 +109,7 @@ string errorMisc = "Sorry, there were some problems with the command you entered
 vector<string> commands{addbooksCmd,
                         compareCmd + "12",
                         jaccardCmd + "12",
+                        nearestCmd + "12",
                         textCmd + "1",
                         textCmd + "2",
                         lookupCmd + "1",
@@ -288,6 +290,9 @@ string getHelp(const string &key)
         "check, best match is reached at 1/(length1+length2).",
         "* `jaccard12`: Compare the two clipboards the same way how `compare12` does but use the "
         "\"Jaccard similarity for bags\" algorithm, best match is reached at 0.",
+        "* `nearest12`: Find a substring of clipboard1 such that its Jaccard similarity for bags "
+        " to clipboard2 is minimal.",
+        "\"Jaccard similarity for bags\" algorithm, best match is reached at 0.",
         "* `sql` *switch*: Set some outputs to be shown also as an SQL query if *switch* is `on`.",
         "* `colors` *switch*: Show some outputs colored if *switch* is `on`.",
         "* `tokens` *Bible* *book* *verse*: Search for the given *verse* in the given *book* in "
@@ -678,6 +683,18 @@ void processJaccardCmd()
     }
 }
 
+void processNearestCmd()
+{
+    if (textset.at(0) && textset.at(1)) {
+        string best_c_d = best_jaccard_substr(text[1], text[0]);
+        vector<string> tokens;
+        boost::split(tokens, best_c_d, boost::is_any_of(" "));
+        info("Nearest Jaccard distance is " + tokens[1] + " with substring " + tokens[0] + ".");
+    } else {
+        error("Text 1 or 2 is not set.");
+    }
+}
+
 void processPsalminfoCmd(string input)
 {
     vector<string> tokens;
@@ -960,6 +977,8 @@ string cli_process(char *buf)
         processCompareCmd();
     else if (boost::starts_with(input, jaccardCmd + "12"))
         processJaccardCmd();
+    else if (boost::starts_with(input, nearestCmd + "12"))
+        processNearestCmd();
     else if (boost::starts_with(input, minuniqueCmd + "1"))
         processMinuniqueCmd(input);
     // TODO: Consider using this trick for the other commands:

cli.h

@@ -1,7 +1,7 @@
 #ifndef CLI_H
 #define CLI_H
 
-#define BIBREF_VERSION "2025-04-19"
+#define BIBREF_VERSION "2025-07-13"
 
 #include <string>
 

fingerprint.cpp

@@ -136,7 +136,7 @@ string best_jaccard_substr(const string &fixtext, const string &subtext)
                 }
             }
         }
-    return subtext.substr(best_s1, best_s2 - best_s1 + 2);
+    return subtext.substr(best_s1, best_s2 - best_s1 + 2) + " " + to_string(best);
 }
 // Example call:
 // best_jaccard_substr("panarsendianoigonmhtranagiontvkyrivklhuhsetai",

fingerprint.dox

@@ -38,4 +38,5 @@ double jaccard_dist(const string& text1, const string& text2);
 string best_jaccard_substr(const string &fixtext, const string &subtext) {
  /// @param fixtext The fixed text.
  /// @param subtext The text for which a substring must be found.
+ /// @return The nearest substring and the minimal Jaccard distance, separated by a space character.
 };

snapcraft.yaml

@@ -1,6 +1,6 @@
 name: bibref
 base: core20
-version: '2025-04-08'
+version: '2025-07-13'
 summary: A tool that helps discovering internal references in the Bible
 icon: logo-Psalm40-192.png
 description: |