improving documentation in process.cfg

process.cfg

@@ -8,6 +8,8 @@
 # consolidate: if True, runs the conslidation step on the output of clean
 # outputdir: specifies the final destination of the resulting sqlite3 files
 # doctype: can be grant, application, or all, and processing will proceed accordingly
+#          if 'all' is specified, a separate regex should be supplied for
+#          the grants and applications. See the example parse under [download]
 
 [process]
 parse=download
@@ -57,13 +59,20 @@ doctype=all
 [2012parse]
 datadir=/data/patentdata/patents/2012
 
+
+# example configuration to test the parsing
 [test]
 datadir=test/fixtures/xml
 dataregex=\d{4}_\d.xml
 
+# example configuration for a parse of the latest data. Note that the 
+# regexes for grants and applications will be used if 'all' is specified 
+# for doctype in [process]
 [download]
 years=latest
 downloaddir=./data
+grantregex=ipg\d{6}.xml
+applicationregex=i?pa\d{6}.xml
 
 # This section specifies which grant_handler is to be used for each date of the
 # released patent. This section should only have to be touched when a new parser is
@@ -76,9 +85,11 @@ downloaddir=./data
 20130115=lib.handlers.grant_handler_v44
 default=lib.handlers.grant_handler_v42
 
-# schema changes were in 20010131 (v15), 20020101 (v16), 20050825 (v41), 20060823 (v42), 20130121 (v43)
 [application-xml-handlers]
 2001-20060822=lib.handlers.application_handler_v41
 20060823-20130116=lib.handlers.application_handler_v42
 20130117=lib.handlers.application_handler_v43
 default=lib.handlers.application_handler_v42
+
+# schema changes were in 20010131 (v15), 20020101 (v16), 
+# 20050825 (v41), 20060823 (v42), 20130121 (v43)