gnu: Add Swish-e.

* gnu/packages/search.scm (swish-e): New variable.
* gnu/packages/patches/swish-e-search.patch,
gnu/packages/patches/swish-e-format-security.patch: New patches.
* gnu/local.mk (dist_patch_DATA): Add them.

3 files changed, 142 insertions, 1 deletions

diff --git a/gnu/packages/patches/swish-e-format-security.patch b/gnu/packages/patches/swish-e-format-security.patch
new file mode 100644
index 0000000000..be9d7cb8a9
--- /dev/null
+++ b/gnu/packages/patches/swish-e-format-security.patch
@@ -0,0 +1,33 @@
+Borrowed from Debian.
+
+--- swish-e-2.4.7/src/parser.c	2009-04-05 03:58:32.000000000 +0200
++++ swish-e-2.4.7/src/parser.c	2013-06-11 13:53:08.196559035 +0200
+@@ -1760,7 +1760,7 @@
+     va_start(args, msg);
+     vsnprintf(str, 1000, msg, args );
+     va_end(args);
+-    xmlParserError(parse_data->ctxt, str);
++    xmlParserError(parse_data->ctxt, "%s", str);
+ }
+ 
+ static void warning(void *data, const char *msg, ...)
+@@ -1772,7 +1772,7 @@
+     va_start(args, msg);
+     vsnprintf(str, 1000, msg, args );
+     va_end(args);
+-    xmlParserWarning(parse_data->ctxt, str);
++    xmlParserWarning(parse_data->ctxt, "%s", str);
+ }
+ 
+ 
+--- swish-e-2.4.7/src/result_output.c	2009-04-05 03:58:32.000000000 +0200
++++ swish-e-2.4.7/src/result_output.c	2013-06-11 13:53:38.593550825 +0200
+@@ -752,7 +752,7 @@
+             s = (char *) emalloc(MAXWORDLEN + 1);
+             n = strftime(s, (size_t) MAXWORDLEN, fmt, localtime(&(pv->value.v_date)));
+             if (n && f)
+-                fprintf(f, s);
++                fprintf(f, "%s", s);
+             efree(s);
+         }
+         break;
diff --git a/gnu/packages/patches/swish-e-search.patch b/gnu/packages/patches/swish-e-search.patch
new file mode 100644
index 0000000000..2a57a31a08
--- /dev/null
+++ b/gnu/packages/patches/swish-e-search.patch
@@ -0,0 +1,43 @@
+From http://swish-e.org/archive/2015-09/13295.html
+
+--- a/src/compress.c	
++++ a/src/compress.c	
+@@ -995,7 +995,7 @@ void    remove_worddata_longs(unsigned char *worddata,int *sz_worddata)
+             progerr("Internal error in remove_worddata_longs");
+ 
+         /* dst may be smaller than src. So move the data */
+-        memcpy(dst,src,data_len);
++        memmove(dst,src,data_len);
+ 
+         /* Increase pointers */
+         src += data_len;
+--- a/src/headers.c	
++++ a/src/headers.c	
+@@ -280,7 +280,7 @@ static SWISH_HEADER_VALUE fetch_single_header( IndexFILE *indexf, HEADER_MAP *he
+ 
+         case SWISH_NUMBER:
+         case SWISH_BOOL:
+-            value.number = *(unsigned long *) data_pointer;
++            value.number = *(unsigned int *) data_pointer;
+ 
+             /* $$$ Ugly hack alert! */
+             /* correct for removed files */
+--- a/src/swishspider	
++++ a/src/swishspider	
+@@ -27,6 +27,7 @@ use LWP::UserAgent;
+ use HTTP::Status;
+ use HTML::Parser 3.00;
+ use HTML::LinkExtor;
++use Encode;
+ 
+     if (scalar(@ARGV) != 2) {
+         print STDERR "Usage: $0 localpath url\n";
+@@ -94,7 +95,7 @@ use HTML::LinkExtor;
+     # Don't allow links above the base
+     $URI::ABS_REMOTE_LEADING_DOTS = 1;
+ 
+-    $p->parse( $$content_ref );
++    $p->parse( decode_utf8 $$content_ref );
+     close( LINKS );
+ 
+     exit;
diff --git a/gnu/packages/search.scm b/gnu/packages/search.scm
index 9a7bc76463..60f902f96a 100644
--- a/gnu/packages/search.scm
+++ b/gnu/packages/search.scm
@@ -23,10 +23,14 @@
   #:use-module (guix packages)
   #:use-module (guix download)
   #:use-module (guix build-system gnu)
+  #:use-module (gnu packages)
   #:use-module (gnu packages compression)
   #:use-module (gnu packages check)
   #:use-module (gnu packages databases)
-  #:use-module (gnu packages linux))
+  #:use-module (gnu packages linux)
+  #:use-module (gnu packages perl)
+  #:use-module (gnu packages web)
+  #:use-module (gnu packages xml))
 
 (define-public xapian
   (package
@@ -171,4 +175,65 @@ with slocate, and attempts to be compatible to GNU locate when it does not
 conflict with slocate compatibility.")
     (license gpl2)))
 
+(define-public swish-e
+  (package
+    (name "swish-e")
+    (version "2.4.7")
+    (source (origin
+              (method url-fetch)
+              (uri (list (string-append "http://swish-e.org/distribution/"
+                                        "swish-e-" version ".tar.gz")
+                         ;; The upstream swish-e.org appears to be down... so
+                         ;; use debian's copy as a fallback.
+                         (string-append "http://http.debian.net/debian/pool/"
+                                        "main/s/swish-e/swish-e_" version
+                                        ".orig.tar.gz")))
+              (file-name (string-append name "-" version ".tar.gz"))
+              (sha256
+               (base32
+                "0qkrk7z25yp9hynj21vxkyn7yi8gcagcfxnass5cgczcz0gm9pax"))
+              (patches (search-patches "swish-e-search.patch"
+                                       "swish-e-format-security.patch"))))
+    (build-system gnu-build-system)
+    ;; Several other packages and perl modules may be installed alongside
+    ;; swish-e to extend its features at runtime, but are not required for
+    ;; building: xpdf, catdoc, MP3::Tag, Spreadsheet::ParseExcel,
+    ;; HTML::Entities.
+    (inputs
+     `(("libxml" ,libxml2)
+       ("zlib" ,zlib)
+       ("perl" ,perl)
+       ("perl-uri" ,perl-uri)
+       ("perl-html-parser" ,perl-html-parser)
+       ("perl-html-tagset" ,perl-html-tagset)
+       ("perl-mime-types" ,perl-mime-types)))
+    (arguments
+     `(#:phases (modify-phases %standard-phases
+                  (add-after 'install 'wrap-programs
+                    (lambda* (#:key inputs outputs #:allow-other-keys)
+                      (let* ((out (assoc-ref outputs "out")))
+                        (for-each
+                         (lambda (program)
+                           (wrap-program program
+                             `("PERL5LIB" ":" prefix
+                               ,(map (lambda (i)
+                                       (string-append (assoc-ref inputs i)
+                                                      "/lib/perl5/site_perl"))
+                                     ;; These perl modules have no propagated
+                                     ;; inputs, so no further analysis needed.
+                                     '("perl-uri"
+                                       "perl-html-parser"
+                                       "perl-html-tagset"
+                                       "perl-mime-types")))))
+                         (list (string-append out "/lib/swish-e/swishspider")
+                               (string-append out "/bin/swish-filter-test")))
+                        #t))))))
+    (home-page "http://swish-e.org")
+    (synopsis "Web indexing system")
+    (description
+     "Swish-e is Simple Web Indexing System for Humans - Enhanced.  Swish-e
+can quickly and easily index directories of files or remote web sites and
+search the generated indexes.")
+    (license gpl2+)))                   ;with exception
+
 ;;; search.scm ends here