From c7ae219e399804a8eb33f176e532a79b389ee1f1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ludovic=20Court=C3=A8s?= <ludo@gnu.org>
Date: Wed, 13 Sep 2017 15:07:17 +0200
Subject: ui: Generalize relevance computation.

* guix/ui.scm (relevance, package-relevance): New procedures.
(%package-metrics): New variable.
* guix/scripts/package.scm (find-packages-by-description)[score]
[package-score]: Remove.  Use 'package-relevance' instead.
---
 guix/ui.scm | 43 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 43 insertions(+)

(limited to 'guix/ui.scm')

diff --git a/guix/ui.scm b/guix/ui.scm
index b0108d0705..a51877c04d 100644
--- a/guix/ui.scm
+++ b/guix/ui.scm
@@ -85,6 +85,8 @@
             string->recutils
             package->recutils
             package-specification->name+version+output
+            relevance
+            package-relevance
             string->generations
             string->duration
             matching-generations
@@ -1024,6 +1026,47 @@ WIDTH columns.  EXTRA-FIELDS is a list of symbol/value pairs to emit."
             extra-fields)
   (newline port))
 
+(define (relevance obj regexps metrics)
+  "Compute a \"relevance score\" for OBJ as a function of its number of
+matches of REGEXPS and accordingly to METRICS.  METRICS is list of
+field/weight pairs, where FIELD is a procedure that returns a string
+describing OBJ, and WEIGHT is a positive integer denoting the weight of this
+field in the final score.
+
+A score of zero means that OBJ does not match any of REGEXPS.  The higher the
+score, the more relevant OBJ is to REGEXPS."
+  (define (score str)
+    (let ((counts (filter-map (lambda (regexp)
+                                (match (regexp-exec regexp str)
+                                  (#f #f)
+                                  (m  (match:count m))))
+                              regexps)))
+      ;; Compute a score that's proportional to the number of regexps matched
+      ;; and to the number of matches for each regexp.
+      (* (length counts) (reduce + 0 counts))))
+
+  (fold (lambda (metric relevance)
+          (match metric
+            ((field . weight)
+             (match (field obj)
+               (#f  relevance)
+               (str (+ relevance
+                       (* (score str) weight)))))))
+        0
+        metrics))
+
+(define %package-metrics
+  ;; Metrics used to compute the "relevance score" of a package against a set
+  ;; of regexps.
+  `((,package-name . 3)
+    (,package-synopsis-string . 2)
+    (,package-description-string . 1)))
+
+(define (package-relevance package regexps)
+  "Return a score denoting the relevance of PACKAGE for REGEXPS.  A score of
+zero means that PACKAGE does not match any of REGEXPS."
+  (relevance package regexps %package-metrics))
+
 (define (string->generations str)
   "Return the list of generations matching a pattern in STR.  This function
 accepts the following patterns: \"1\", \"1,2,3\", \"1..9\", \"1..\", \"..9\"."
-- 
cgit v1.2.3