updated recoll.conf doc

src/sampleconf/recoll.conf

@@ -168,14 +168,16 @@ skippedPaths = /media
 # subtrees.</descr></var>
 #excludedmimetypes = 
 
-# <var name="nomd5mimetypes" type="string"><brief>Don't compute md5 for
-# these types.</brief><descr>md5 checksums are used only for deduplicating
-# results, and can be very expensive to compute on multimedia or other big
-# files. This list lets you turn off md5 computation for selected types. It
-# is global (no redefinition for subtrees). At the moment, it only has an
-# effect for external handlers (exec and execm). The file types can be
-# specified by listing either MIME types (e.g. audio/mpeg) or handler names
-# (e.g. rclaudio).</descr></var>
+# <var name="nomd5types" type="string">
+#  <brief>Don't compute md5 for these types.</brief>
+#  <descr>md5 checksums are used only for deduplicating results, and can be
+#  very expensive to compute on multimedia or other big files. This list
+#  lets you turn off md5 computation for selected types. It is global (no
+#  redefinition for subtrees). At the moment, it only has an effect for
+#  external handlers (exec and execm). The file types can be specified by
+#  listing either MIME types (e.g. audio/mpeg) or handler names
+#  (e.g. rclaudio).</descr>
+# </var>
 nomd5types = rclaudio
 
 # <var name="compressedfilemaxkbs" type="int"><brief>Size limit for compressed
@@ -299,6 +301,21 @@ indexStoreDocText = 1
 # restoring the previous behaviour.</descr></var>
 #dehyphenate = 1
 
+# <var name="backslashasletter" type="bool">
+#  <brief>Process backslash as normal letter</brief>
+#  <descr>This may make sense for people wanting to index TeX commands as
+#  such but is not of much general use.</descr>
+# </var>
+#backslashasletter = 0
+
+# <var name="maxtermlength" type="int" values="10 200 40">
+#  <brief>Maximum term length.</brief>
+#  <descr>Words longer than this will be discarded.
+#  The default is 40 and used to be hard-coded, but it can now be
+#  adjusted. You need an index reset if you change the value.</descr>
+# </var>
+#maxtermlength = 40
+
 # <var name="nocjk" type="bool"><brief>Decides if specific East Asian
 # (Chinese Korean Japanese) characters/word splitting is turned
 # off.</brief><descr>This will save a small amount of CPU if you have no CJK
@@ -435,7 +452,7 @@ noxattrfields = 0
 # value is 0, meaning no checking.</descr></var>
 maxfsoccuppc = 0
 
-# <var name="xapiandb" type="dfn"><brief>Xapian database directory
+# <var name="dbdir" type="dfn"><brief>Xapian database directory
 # location.</brief><descr>This will be created on first indexing. If the
 # value is not an absolute path, it will be interpreted as relative to
 # cachedir if set, or the configuration directory (-c argument or
@@ -837,6 +854,14 @@ snippetMaxPosWalk = 1000000
 # very slow.</descr></var>
 #pdfocr = 0
 
+# <var name="pdfocrlang" type="string">
+#  <brief>Language to assume for PDF OCR.</brief>
+#  <descr>This is very important for having a reasonable rate of errors
+#   with tesseract. This can also be set through a configuration variable
+#   or directory-local parameters. See the rclpdf.py script.</descr>
+# </var>
+#pdfocrlang = eng
+
 # <var name="pdfattach" type="bool">
 #
 # <brief>Enable PDF attachment extraction by executing pdftk (if