added adaptor script for new browser plugin

src/filters/recoll-we-move-files.py

@@ -0,0 +1,136 @@
+#!/usr/bin/env python3
+# Copyright (C) 2017 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
+#  (at your option) any later version.
+#
+#  This program is distributed in the hope that it will be useful,
+#  but WITHOUT ANY WARRANTY; without even the implied warranty of
+#  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+#  GNU General Public License for more details.
+#
+#  You should have received a copy of the GNU General Public License
+#  along with this program; if not, write to the
+#  Free Software Foundation, Inc.,
+#  59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
+
+""" Monitor download directory for pages created by the recoll-we extension.
+
+The files (content file and metadata side file) are then renamed and
+moved to the Recoll web queue directory.
+
+We recognize recoll files by their pattern:
+recoll-we-[cm]-<md5>.rclwe, and the fact that both a d and an m file
+must exist. While not absolutely foolproof, this should be quite robust.
+
+The script is normally executed by recollindex at appropriate times,
+but it can also be run by hand.
+"""
+
+import sys
+import os
+import re
+try:
+    from hashlib import md5 as md5
+except:
+    import md5
+import shutil
+
+try:
+    from recoll import rclconfig
+except:
+    import rclconfig
+
+def logdeb(s):
+    print("%s"%s, file=sys.stderr)
+
+# # wnloaded instances of the same page are suffixed with (nn) by the
+# browser.  We are passed a list of (hash, instancenum, filename)
+# triplets, sort it, and keep only the latest file.
+def delete_previous_instances(l, downloadsdir):
+    l.sort(key = lambda e: "%s-%05d"%(e[0], e[1]), reverse=True)
+    ret = {}
+    i = 0
+    while i < len(l):
+        hash,num,fn = l[i]
+        logdeb("Found %s"%fn)
+        ret[hash] = fn
+        j = 1
+        while i + j < len(l):
+            if l[i+j][0] == hash:
+                ofn = l[i+j][2]
+                logdeb("Deleting %s"%ofn)
+                os.unlink(os.path.join(downloadsdir, ofn))
+                j += 1
+            else:
+                break
+        i += j
+    return ret
+
+fn_re = re.compile('''recoll-we-([mc])-([0-9a-f]+)(\([0-9]+\))?\.rclwe''')
+
+def list_all_files(dir):
+    files=os.listdir(dir)
+    mfiles = []
+    cfiles = []
+    for fn in files:
+        mo = fn_re.match(fn)
+        if mo:
+            mc = mo.group(1)
+            hash = mo.group(2)
+            num = mo.group(3)
+            if not num:
+                num = "(0)"
+            num = int(num.strip("()"))
+            if mc == 'm':
+                mfiles.append([hash, num, fn])
+            else:
+                cfiles.append([hash, num, fn])
+    return mfiles,cfiles
+
+#######################
+def usage():
+    print("Usage: recoll-we-move-files.py [<downloaddir>]", file=sys.stderr)
+    sys.exit(1)
+
+# Source dir is parameter, else default Downloads directory
+downloadsdir = os.path.expanduser("~/Downloads")
+if len(sys.argv) == 2:
+    mydir = sys.argv[1]
+elif len(sys.argv) == 1:
+    mydir = downloadsdir
+else:
+    usage()
+if not os.path.isdir(mydir):
+    usage()
+
+# Get target webqueue recoll directory from recoll configuration
+config = rclconfig.RclConfig()
+webqueuedir = config.getConfParam("webqueuedir")
+if not webqueuedir:
+    webqueuedir = "~/.recollweb/ToIndex"
+webqueuedir = os.path.expanduser(webqueuedir)
+logdeb("webqueuedir is %s" % webqueuedir)
+
+# Get the lists of all files created by the browser addon
+mfiles, cfiles = list_all_files(mydir)
+
+# Only keep the last version
+mfiles = delete_previous_instances(mfiles, downloadsdir)
+cfiles = delete_previous_instances(cfiles, downloadsdir)
+
+#logdeb("Mfiles: %s"% mfiles)
+#logdeb("Cfiles: %s"% cfiles)
+
+# Move files to webqueuedir target directory
+# The webextensions plugin creates the metadata files first. So it may
+# happen that a data file is missing, keep them for next pass.
+# The old plugin created the data first, so we move data then meta
+for hash in cfiles.keys():
+    if hash in mfiles.keys():
+        newname = "firefox-recoll-web-"+hash
+        shutil.move(cfiles[hash], os.path.join(webqueuedir, newname))
+        shutil.move(mfiles[hash], os.path.join(webqueuedir, "." + newname))
+
+

src/sampleconf/recoll.conf

@@ -430,9 +430,12 @@ webcachemaxmbs = 40
 
 # <var name="webqueuedir" type="fn">
 #
-# <brief>The path to the Web indexing queue.</brief><descr>This is
-# hard-coded in the plugin as ~/.recollweb/ToIndex so there should be no
-# need or possibility to change it.</descr></var>
+# <brief>The path to the Web indexing queue.</brief><descr>This used to be
+# hard-coded in the old plugin as ~/.recollweb/ToIndex so there would be no
+# need or possibility to change it, but the WebExtensions plugin now downloads
+# the files to the user Downloads directory, and a script moves them to
+# webqueuedir. The script reads this value from the config so it has become
+# possible to change it.</descr></var>
 #webqueuedir = ~/.recollweb/ToIndex
 
 # <var name="aspellDicDir" type="dfn">