document the new ocr function and its config

src/sampleconf/recoll.conf

@@ -350,7 +350,8 @@ indexStoreDocText = 1
 #
 # <brief>Languages for which to create stemming expansion
 # data.</brief><descr>Stemmer names can be found by executing 'recollindex
-# -l', or this can also be set from a list in the GUI.</descr></var>
+# -l', or this can also be set from a list in the GUI. The values are full
+# language names, e.g. english, french...</descr></var>
 indexstemminglanguages = english 
 
 # <var name="defaultcharset" type="string"><brief>Default character
@@ -760,9 +761,9 @@ checkneedretryindexscript = rclcheckneedretry.sh
 #
 # <brief>Language definitions to use when creating the aspell
 # dictionary.</brief><descr>The value must match a set of aspell language
-# definition files. You can type "aspell dicts"  to see a list The default
-# if this is not set is to use the NLS environment to guess the
-# value.</descr></var>
+# definition files. You can type "aspell dicts" to see a list The default
+# if this is not set is to use the NLS environment to guess the value. The
+# values are the 2-letter language codes (e.g. 'en', 'fr'...)</descr></var>
 #aspellLanguage = en
 
 # <var name="aspellAddCreateParam" type="string">
@@ -902,19 +903,11 @@ snippetMaxPosWalk = 1000000
 
 # <var name="pdfocr" type="bool">
 #
-# <brief>Attempt OCR of PDF files with no text content if both tesseract and
-# pdftoppm are installed.</brief>
+# <brief>Attempt OCR of PDF files with no text content.</brief>
 # <descr>This can be defined in subdirectories. The default is off because
-# OCR is so 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>
+# OCR is so very slow. Will only do anything if ocrprogs is defined.</descr>
 # </var>
-#pdfocrlang = eng
+#pdfocr = 0
 
 # <var name="pdfattach" type="bool">
 #
@@ -946,6 +939,60 @@ snippetMaxPosWalk = 1000000
 #pdfextrametafix =  /path/to/fixerscript.py
 
 
+# <grouptitle id="OCR">Parameters for OCR processing</grouptitle>
+
+
+# <var name="ocrprogs" type="string">
+# <brief>OCR modules to try.</brief>
+# <descr>The top OCR script will try to load the corresponding modules in
+# order and use the first which reports being capable of performing OCR on
+# the input file. Modules for tesseract and ABBYY FineReader are present in
+# the standard distribution.</descr>
+# </var>
+#ocrprogs = abbyy tesseract
+
+# <var name="ocrcachedir" type="dfn">
+# <brief>Location for caching OCR data.</brief>
+# <descr>The default if this is empty or undefined is to store the cached
+# OCR data under $RECOLL_CONFDIR/ocrcache.</descr>
+# </var>
+#ocrcachedir=
+
+
+# <var name="tesseractlang" type="string">
+#  <brief>Language to assume for tesseract OCR.</brief>
+#  <descr>Important for improving the OCR accuracy. This can also be set
+#  through the contents of a file in
+#  the currently processed directory. See the rclocrtesseract.py
+#  script. Example values: eng, fra... See the tesseract documentation.</descr>
+# </var>
+#tesseractlang = eng
+
+# <var name="tesseractcmd" type="fn">
+# <brief>Path for the tesseract command.</brief>
+# <descr>This is mostly useful on Windows, or for specifying a non-default
+# tesseract command. e.g. on Windows:
+# C:/Program&nbsp;Files&nbsp;(x86)/Tesseract-OCR/tesseract.exe</descr>
+# </var>
+#tesseractcmd = c:/Program Files (x86)/Tesseract-OCR/tesseract.exe
+
+# <var name="abbyylang" type="string">
+# <brief>Language to assume for abbyy OCR.</brief>
+# <descr>Important for improving the OCR accuracy. This can also be set
+# through the contents of a file in
+# the currently processed directory. See the rclocrabbyy.py
+# script. Typical values: English, French... See the ABBYY documentation.
+# </descr>
+# </var>
+#abbyylang = English
+
+# <var name="abbyycmd" type="fn">
+# <brief>Path for the abbyy command</brief>
+# <descr>The ABBY directory is usually not in the path, so you should set this.
+# </descr>
+# </var>
+abbyycmd = /opt/ABBYYOCR11/abbyyocr11
+
 # <grouptitle id="SPECLOCATIONS">Parameters set for specific
 # locations</grouptitle>