all messages for Guix-related lists mirrored at yhetil.org
 help / color / mirror / code / Atom feed
From: Arun Isaac <arunisaac@systemreboot.net>
To: 39258@debbugs.gnu.org
Cc: Arun Isaac <arunisaac@systemreboot.net>
Subject: [bug#39258] [PATCH 2/4] ui: Use string matching with literal search strings.
Date: Mon,  1 Jun 2020 05:30:28 +0530	[thread overview]
Message-ID: <20200601000030.7443-3-arunisaac@systemreboot.net> (raw)
In-Reply-To: <20200601000030.7443-1-arunisaac@systemreboot.net>

* guix/scripts/package.scm (process-query): Make search query a regexp only if
it is not a literal search string.
* guix/ui.scm (relevance): Use string matching with literal search strings and
regexp matching with regexp search strings.
---
 guix/scripts/package.scm | 12 +++++++---
 guix/ui.scm              | 50 +++++++++++++++++++++++++---------------
 2 files changed, 40 insertions(+), 22 deletions(-)

diff --git a/guix/scripts/package.scm b/guix/scripts/package.scm
index 1246147798..1b637f7802 100644
--- a/guix/scripts/package.scm
+++ b/guix/scripts/package.scm
@@ -675,6 +675,11 @@ doesn't need it."
 (define (process-query opts)
   "Process any query specified by OPTS.  Return #t when a query was actually
 processed, #f otherwise."
+  (define (regexp-pattern? str)
+    (string-any
+     (char-set #\. #\[ #\{ #\} #\( #\) #\\ #\* #\+ #\? #\| #\^ #\$)
+     str))
+
   (let* ((profiles (delete-duplicates
                     (match (filter-map (match-lambda
                                          (('profile . p) p)
@@ -781,11 +786,12 @@ processed, #f otherwise."
 
       (('search _)
        (let* ((patterns (filter-map (match-lambda
-                                      (('query 'search rx) rx)
+                                      (('query 'search (? regexp-pattern? rx))
+                                       (make-regexp* rx regexp/icase))
+                                      (('query 'search pattern) pattern)
                                       (_                   #f))
                                     opts))
-              (regexps  (map (cut make-regexp* <> regexp/icase) patterns))
-              (matches  (find-packages-by-description regexps)))
+              (matches  (find-packages-by-description patterns)))
          (leave-on-EPIPE
           (display-search-results matches (current-output-port)))
          #t))
diff --git a/guix/ui.scm b/guix/ui.scm
index 4a22358963..56754dba83 100644
--- a/guix/ui.scm
+++ b/guix/ui.scm
@@ -1489,41 +1489,53 @@ HYPERLINKS? is true, emit hyperlink escape sequences when appropriate."
 ;;; Searching.
 ;;;
 
-(define (relevance obj regexps metrics)
+(define (relevance obj patterns 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
+matches of PATTERNS and accordingly to METRICS.  METRICS is list of
 field/weight pairs, where FIELD is a procedure that returns a string or list
 of strings 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 regexp str)
-    (fold-matches regexp str 0
-                  (lambda (m score)
-                    (+ score
-                       (if (string=? (match:substring m) str)
-                           5             ;exact match
-                           1)))))
-
-  (define (regexp->score regexp)
-    (let ((score-regexp (lambda (str) (score regexp str))))
+A score of zero means that OBJ does not match any of PATTERNS.  The higher the
+score, the more relevant OBJ is to PATTERNS."
+  (define (score pattern str)
+    (match pattern
+      ((? string? pattern)
+       (cond
+        ((string=? str pattern) 5)
+        (else
+         (let loop ((score 0) (start 0))
+           (cond
+            ((string-contains-ci str pattern start)
+             => (lambda (index)
+                  (loop (+ score 1) (+ index (string-length pattern)))))
+            (else score))))))
+      ((? regexp? regexp)
+       (fold-matches regexp str 0
+                     (lambda (m score)
+                       (+ score
+                          (if (string=? (match:substring m) str)
+                              5             ;exact match
+                              1)))))))
+
+  (define (pattern->score pattern)
+    (let ((score-pattern (lambda (str) (score pattern str))))
       (fold (lambda (metric relevance)
               (match metric
                 ((field . weight)
                  (match (field obj)
                    (#f  relevance)
                    ((? string? str)
-                    (+ relevance (* (score-regexp str) weight)))
+                    (+ relevance (* (score-pattern str) weight)))
                    ((lst ...)
-                    (+ relevance (* weight (apply + (map score-regexp lst)))))))))
+                    (+ relevance (* weight (apply + (map score-pattern lst)))))))))
             0 metrics)))
 
-  (let loop ((regexps regexps)
+  (let loop ((patterns patterns)
              (total-score 0))
-    (match regexps
+    (match patterns
       ((head . tail)
-       (let ((score (regexp->score head)))
+       (let ((score (pattern->score head)))
          ;; Return zero if one of PATTERNS doesn't match.
          (cond
           ((zero? score) 0)
-- 
2.26.2





  parent reply	other threads:[~2020-06-01  0:01 UTC|newest]

Thread overview: 126+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-01-23 19:51 [bug#39258] Faster guix search using an sqlite cache Arun Isaac
2020-01-29 23:33 ` zimoun
2020-01-30 13:48   ` Arun Isaac
2020-01-31 12:48     ` zimoun
2020-02-02 21:16       ` Arun Isaac
2020-02-04 10:19         ` zimoun
2020-02-06  1:58           ` Arun Isaac
2020-02-11 16:29             ` Ludovic Courtès
2020-02-11 18:21               ` zimoun
2020-02-11 18:39                 ` Ludovic Courtès
2020-02-11 19:07                   ` Arun Isaac
2020-02-11 20:20                     ` zimoun
2020-02-15 14:50                     ` Arun Isaac
2020-02-11 20:13                   ` zimoun
2020-02-27 20:41 ` [bug#39258] [PATCH 0/4] Xapian for Guix package search Arun Isaac
2020-02-27 20:41   ` [bug#39258] [PATCH 1/4] gnu: Add guile-xapian Arun Isaac
2020-03-03 16:29     ` zimoun
2020-02-27 20:41   ` [bug#39258] [PATCH 2/4] build-self: Add guile-xapian to Guix dependencies Arun Isaac
2020-02-27 20:41   ` [bug#39258] [PATCH 3/4] gnu: Generate xapian package search index Arun Isaac
2020-02-28  8:04     ` Pierre Neidhardt
2020-03-05 20:26       ` Arun Isaac
2020-03-03 18:29     ` zimoun
2020-02-27 20:41   ` [bug#39258] [PATCH 4/4] gnu: Use xapian index for package search Arun Isaac
2020-02-28  8:11     ` Pierre Neidhardt
2020-03-03 19:21     ` zimoun
2020-03-03 19:51       ` zimoun
2020-02-28  8:13   ` [bug#39258] [PATCH 0/4] Xapian for Guix " Pierre Neidhardt
2020-02-28 12:39     ` zimoun
2020-02-28 12:49       ` Pierre Neidhardt
2020-02-28 15:36     ` Arun Isaac
2020-02-28 16:04       ` Arun Isaac
2020-03-02 18:37         ` zimoun
2020-03-02 19:13           ` zimoun
2020-03-03 20:04             ` zimoun
2020-02-29  8:25       ` Arun Isaac
2020-03-02 18:27         ` zimoun
2020-02-28 12:36   ` zimoun
2020-03-05 16:46   ` Ludovic Courtès
2020-03-07 13:31 ` [bug#39258] [PATCH v2 0/3] " Arun Isaac
2020-03-07 13:31   ` [bug#39258] [PATCH v2 1/3] build-self: Add guile-xapian to Guix dependencies Arun Isaac
2020-03-09 18:14     ` zimoun
2020-03-09 23:40     ` Jonathan Brielmaier
2020-03-10  5:24       ` Arun Isaac
2020-03-07 13:31   ` [bug#39258] [PATCH v2 2/3] gnu: Generate Xapian package search index Arun Isaac
2020-03-09 18:19     ` zimoun
2020-03-07 13:31   ` [bug#39258] [PATCH v2 3/3] gnu: Use Xapian index for package search Arun Isaac
2020-03-07 20:33   ` [bug#39258] [PATCH v2 0/3] Xapian for Guix " Ludovic Courtès
2020-03-08  9:01     ` Arun Isaac
2020-03-08 11:33       ` Ludovic Courtès
2020-03-08 20:27         ` Arun Isaac
2020-03-09  7:42           ` Pierre Neidhardt
2020-03-09 12:50             ` zimoun
2020-03-09 10:35           ` Ludovic Courtès
2020-03-10 14:17             ` Arun Isaac
2020-03-10 14:33               ` zimoun
2020-03-11 13:50               ` Ludovic Courtès
2020-03-13  5:37                 ` Arun Isaac
2020-03-15 20:40                   ` Ludovic Courtès
2020-03-09  7:50         ` Pierre Neidhardt
2020-03-09 10:28           ` Ludovic Courtès
2020-03-09 13:03             ` zimoun
2020-03-09 12:53           ` zimoun
2020-03-09 12:47         ` zimoun
2020-03-09 12:40       ` zimoun
2020-03-09 12:34     ` zimoun
2020-03-08 20:27   ` zimoun
2020-03-08 20:40     ` Arun Isaac
2020-03-09 12:28   ` zimoun
2020-03-27 16:26 ` [bug#39258] [PATCH v3 0/3] Package metadata cache for guix search Arun Isaac
2020-03-27 16:26   ` [bug#39258] [PATCH v3 1/3] guix: Generate package metadata cache Arun Isaac
2020-04-24 20:48     ` Ludovic Courtès
2020-04-26  9:48       ` zimoun
2020-04-26 14:35         ` Ludovic Courtès
2020-04-26 14:54           ` Pierre Neidhardt
2020-04-26 15:33             ` Ludovic Courtès
2020-04-26 15:05           ` zimoun
2020-03-27 16:26   ` [bug#39258] [PATCH v3 2/3] guix: Search " Arun Isaac
2020-04-24 20:58     ` Ludovic Courtès
2020-03-27 16:26   ` [bug#39258] [PATCH v3 3/3] guix: Use package metadata cache for package search Arun Isaac
2020-04-24 21:03     ` Ludovic Courtès
2020-04-05 14:08   ` [bug#39258] [PATCH v3 0/3] Package metadata cache for guix search Ludovic Courtès
2020-04-24 21:05   ` Ludovic Courtès
2020-04-26  3:54 ` [bug#39258] benchmark search: default vs v2 vs v3 zimoun
2020-04-26  7:29   ` Pierre Neidhardt
2020-04-26 15:49   ` Ludovic Courtès
2020-04-26 17:01     ` zimoun
2020-04-26 20:22       ` Ludovic Courtès
2020-04-30 13:10     ` zimoun
2020-05-03 15:01 ` [bug#39258] [PATCH v4 0/3] Faster cache generation (similar as v3) zimoun
2020-05-03 15:01   ` [bug#39258] [PATCH v4 1/3] DRAFT packages: Add fields to packages cache zimoun
2020-05-03 15:01   ` [bug#39258] [PATCH v4 2/3] DRAFT packages: Add new procedure 'fold-packages*' zimoun
2020-05-03 15:01   ` [bug#39258] [PATCH v4 3/3] DRAFT guix package: Use cache in 'find-packages-by-description' zimoun
2020-05-03 16:43   ` [bug#39258] [PATCH v4 0/3] Faster cache generation (similar as v3) Ludovic Courtès
2020-05-03 18:10     ` zimoun
2020-05-03 19:49       ` Ludovic Courtès
2020-06-01  0:00 ` [bug#39258] [PATCH 0/4] Optimize guix search Arun Isaac
2020-06-01  0:00   ` [bug#39258] [PATCH 1/4] ui: Cut off search early if any regexp does not match Arun Isaac
2020-06-09  8:29     ` Ludovic Courtès
2020-06-01  0:00   ` Arun Isaac [this message]
2020-06-09  8:33     ` [bug#39258] [PATCH 2/4] ui: Use string matching with literal search strings Ludovic Courtès
2020-06-09  9:55       ` zimoun
2020-06-13 12:37       ` Arun Isaac
2020-06-13 13:36         ` zimoun
2020-06-13 17:21           ` Arun Isaac
2020-06-14 19:14             ` zimoun
2020-06-13 19:32         ` Ludovic Courtès
2020-06-15 20:18           ` Arun Isaac
2020-06-01  0:00   ` [bug#39258] [PATCH 3/4] ui: Do not translate package synopsis a second time Arun Isaac
2020-06-09  8:33     ` Ludovic Courtès
2020-06-01  0:00   ` [bug#39258] [PATCH 4/4] ui: Use package-description-string Arun Isaac
2020-06-09  8:34     ` Ludovic Courtès
2020-06-01  1:25   ` [bug#39258] [PATCH v5 0/4] Optimize guix search zimoun
2020-06-01  2:24     ` Arun Isaac
2020-06-01 10:01     ` zimoun
2020-06-01 10:11 ` [bug#39258] KMP string search algorithm? zimoun
2020-06-01 22:24   ` Leo Famulari
2020-06-01 23:48     ` Arun Isaac
2020-06-02  8:49       ` Ludovic Courtès
2021-07-15  7:33 ` [bug#39258] [PATCH v6 0/2] DRAFT "guix search" performances zimoun
2021-07-15  7:33   ` [bug#39258] [PATCH v6 1/2] DRAFT packages: Add fields to packages cache zimoun
2021-07-17  8:31     ` Arun Isaac
2021-07-23 15:30       ` Ludovic Courtès
2021-08-17 14:03         ` zimoun
2021-07-15  7:33   ` [bug#39258] [PATCH v6 2/2] DRAFT scripts: package: Use cache in 'find-packages-by-description' zimoun
2021-07-23 15:43   ` [bug#39258] [PATCH v6 0/2] DRAFT "guix search" performances Ludovic Courtès
2021-08-20 15:42     ` zimoun

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200601000030.7443-3-arunisaac@systemreboot.net \
    --to=arunisaac@systemreboot.net \
    --cc=39258@debbugs.gnu.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
Code repositories for project(s) associated with this external index

	https://git.savannah.gnu.org/cgit/guix.git

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.