From: Ian Jackson <ian@liberator.relativity.greenend.org.uk>
Date: Fri, 3 Jul 2009 19:58:02 +0000 (+0100)
Subject: New newcommods machinery for ignoring new commodities
X-Git-Tag: 1.9.2~54^2~2
X-Git-Url: https://www.chiark.greenend.org.uk/ucgi/~yarrgweb/git?p=ypp-sc-tools.db-test.git;a=commitdiff_plain;h=17d7ef99b6c9283a0a576febd07c5ebf32b34978;ds=sidebyside

New newcommods machinery for ignoring new commodities
---

diff --git a/pctb/README b/pctb/README
index e9f4f09..f20ebb8 100644
--- a/pctb/README
+++ b/pctb/README
@@ -75,6 +75,24 @@ The program reads and writes the following files:
    it.  Don't try `display vid:#pages#.pnm' as this will consume
    truly stupendous quantities of RAM - it wedged my laptop.
 
+ * #master-newcommods#.txt #local-newcommods#.txt
+
+   Dictionary of newly introduced commodities.  When a new commodity
+   appears in Puzzle Pirates, the PCTB server operators need to add it
+   to their database for us to be able to upload data about it.
+
+   It can sometimes take a few days to do this.  In the meantime, it
+   is possible to upload partial data - data just omitting that
+   commodity.  This is controlled by these files: they list
+   commodities which should be automatically ignored if the PCTB
+   server doesn't know about them.  The master file is downloaded and
+   updated automatically from my server.  You may create the local
+   file yourself.  The format is simple: one commodity per line.
+
+   Unrecognised commodities can also be due to OCR failure so
+   double-check what you're doing before overriding the uploader by
+   telling it to ignore an unrecognised commodity.
+
  * #master-char*#.txt  #local-char*#.txt
    #master-pixmap#.txt #local-pixmap#.txt
 
diff --git a/pctb/README.privacy b/pctb/README.privacy
index a59a2ad..fa63dea 100644
--- a/pctb/README.privacy
+++ b/pctb/README.privacy
@@ -29,9 +29,10 @@ won't happen.
 2. YPP SC PCTB client dictionary server
 =======================================
 
-This server maintains the master database of character and island name
-images, which is used for the commodity screen OCR and also for
-determining your island name.
+This server maintains the master databases of character and island
+name images, and of new commodity names, which is used for the
+commodity screen OCR, for determining your island name, and for
+checking whether commodities not found on the PCTB server are real.
 
 By default, we ask the server for an updated set of dictionaries every
 time we run; this is done with the rsync protocol (indeed, by invoking
diff --git a/pctb/commod-results-processor b/pctb/commod-results-processor
index c3cbe8e..e3f45d1 100755
--- a/pctb/commod-results-processor
+++ b/pctb/commod-results-processor
@@ -295,6 +295,39 @@ sub refresh_commodmap() {
     rename "#commodmap#.tsv.new","#commodmap#.tsv" or die $!;
 }
 
+our %newcommods;
+
+sub read_newcommods ($) {
+    my ($file) = @_;
+    if (!open NC, "< $file") {
+	$!==&ENOENT or die $!;
+	return;
+    }
+    while (<NC>) {
+	chomp; s/^\s*//; s/\s+$//;
+	next if m/^\#/;
+	next unless m/\S/;
+	$newcommods{$_}= 1;
+    }
+    NC->error and die $!;
+    close NC or die $!;
+}
+
+sub refresh_newcommods() {
+    my $rsync= $ENV{'YPPSC_PCTB_RSYNC'};
+    $rsync= 'rsync' if !defined $rsync;
+
+    my $local= "#master-newcommods#.txt";
+    my $src= $ENV{'YPPSC_PCTB_DICT_UPDATE'};
+    if ($src) {
+	my $remote= "$src/master-newcommods.txt";
+	$!=0; system 'rsync','-Lt','--',$remote,$local;
+	die "$? $!" if $! or $?;
+    }
+    read_newcommods($local);
+    read_newcommods('#local-newcommods#.txt');
+}
+
 our (%stallmap, @stallmap);
 
 sub bs_gen_md ($$) {
@@ -302,9 +335,11 @@ sub bs_gen_md ($$) {
     my $count= 0;
     my $o= '';
     
-    foreach $commod (sort {
-	$commodmap{$a} <=> $commodmap{$b}
-    } keys %commod) {
+    foreach $commod (
+		     sort { $commodmap{$a} <=> $commodmap{$b} }
+		     grep { exists $commodmap{$_} }
+		     keys %commod
+		     ) {
 #print STDERR "COMMOD $commod\n";
         $current= $commod{$commod};
 	my $l= bs_p($commod,$bs,$sortmul);
@@ -350,13 +385,19 @@ sub genmarketdata () {
     my @missing= grep { !exists $commodmap{$_} } keys %commod;
     if (@missing) {
 	refresh_commodmap();
+	refresh_newcommods();
 	my $missing=0;
 	foreach $commod (sort keys %commod) {
 	    next if exists $commodmap{$commod};
-	    printf STDERR "Unknown commodity \`%s'!\n", $commod;
-	    $missing++;
+	    if (exists $newcommods{$commod}) {
+		printf STDERR "Ignoring new commodity \`%s'!\n", $commod;
+	    } else {
+		printf STDERR "Unknown commodity \`%s'!\n", $commod;
+		$missing++;
+	    }
 	}
-	die "$missing unknown commoditi(es).  OCR failure?\n"
+	die "$missing unknown commoditi(es).".
+	    "  See README (search for \`newcommods').\n"
 	    if $missing;
     }