Changeset 34130 for main

Timestamp:

2020-05-30T01:27:03+12:00 (4 years ago)

Author:

ak19

Message:

Some more tidying up while isMRI filtered collection rebuilding

File:

• main/trunk/greenstone2/perllib/plugins/NutchTextDumpPlugin.pm (modified) (4 diffs)

main/trunk/greenstone2/perllib/plugins/NutchTextDumpPlugin.pm

@@ -576 +576 @@
         
         # add meta to docObject if both metaname and metavalue are non-empty strings
-        if($metaname ne "" && $metavalue ne "") { # && $metaname ne "rs" && $metaname ne "csh") {
-             # when no namespace is provided as here, adds as ex. meta.
+        if($metaname ne "" && $metavalue ne "") {
+            # when no namespace is provided as here, adds as ex. meta.
             # Don't explicitly prefix ex., as things becomes convoluted when retrieving meta
             $doc_obj->add_utf8_metadata ($cursection, $metaname, $metavalue);
@@ -679 +679 @@
 }
 
+# returns siteID when file in import of form siteID.txt
+# returns siteID when import contains siteID/dump.txt (as happens when OIDtype=dirname)
+# Returns whatever baseOID in other situations, not sure if meaningful, but shouldn't have
+# passed can_process_this_file() test for anything other than siteID/dump.txt and siteID.txt anyway
 sub get_siteID {
     my $self = shift(@_);
@@ -687 +691 @@
     # file name without extension is site ID, e.g. 00001.txt
     $siteID = $1;
-    #$siteID = $file;
-    #$siteID =~ s@\.txt$@@;
     }
     else { # if($doc_obj->{'OIDtype'} eq "dirname") or even otherwise, just use baseOID
@@ -704 +706 @@
 
 # SplitTextFile::get_base_OID() has the side-effect of calling SUPER::add_OID()
-# inorder to initialise it. This then ultimately results in calling util::tidy_up_OID() to print warning messages
-# about all-numeric baseOID requiring the D prefix prepended.
-# When the base_OID is already set and we want to get the baseOID without that side-effect, because siteID = baseOID
-# in cases where OIDtype=dirname.
-# We don't want to recalculate baseOID for each segment, only once per dump.txt file as the superclass SplitTextFile
-# did it. However, we need access to the baseOID from this plugin
-# So we override this method to store the calculated baseOID in a variable for use and check if it's set before
-# calling this method.
-# CANNOT override this method in the usual way though: to calculate baseOID once per dump.txt, store it and return
-# the stored value for each segment because the superclass version of get_base_OID has a side-effect and needs to
-# continue doing everything it usually does each time the superclass calls this method.
+# in order to initialise segment IDs.
+# This then ultimately results in calling util::tidy_up_OID() to print warning messages
+# about siteIDs forming all-numeric baseOIDs that require the D prefix prepended.
+# In cases where site ID is the same as baseOID and is needed to set siteID meta, we want to avoid
+# the warning messages but don't want to prevent the important side-effects of SplitTextFile::get_base_OID()
+# So instead of overriding this method to calculate and store baseOID the first time and return
+# the stored value subsequent times (which has the undesirable result that the side-effect from
+# ALWAYS calling super's get_base_OID() even when there's a stored value), we just always store
+# the return value before returning it. Next, we push the check for first testing for a stored value
+# to use, else forcing it to be computed by calling this get_base_OID(), onto a separate function that
+# calls this one, get_siteID(). Problem solved.
 sub get_base_OID {
     my $self = shift(@_);
     my ($doc_obj) = @_;
 
-
-    # Let this method do what it always did, as it does more than return a value and has important side-effects!
-    # SplitTextPlugin calls this method once for every segment, not just for the base document, with the side-effect
-    # of calculating and adding the OID for each segment.
-    # Therefore, do not return the stored dirname_siteID if already set, as otherwise this method will have
-    # the ominous side-effect of "Warning: D00001s1 already exists with index status I" messages for every segment!
-    # Instead, when trying to work out $siteID (when OIDtype=dirname), check if $self->{'dirname_siteID'} already set
-    # and use that else call this method.
-    #if(!defined $self->{'dirname_siteID'}) {
+    #if(!defined $self->{'dirname_siteID'}) { # DON'T DO THIS: loses essential side-effect of always calling super's get_base_OID()
+    # this method is overridden, so it's not just called by this NutchTextDumpPlugin
+
     $self->{'dirname_siteID'} = $self->SUPER::get_base_OID($doc_obj); # store for NutchTextDumpPlugin's internal use
     #}