<tab><author>[<tab><author>]... # # eg # # - 19891228 - n ---- The Golden Apple Shea R. Wilson R. A. # - 19920516 2 n 1972 A Transatlantic Tunnel Hurrah! Harrison Harry # 19950717 19950726 7 n 1974 The Mote in God's Eye Niven Larry Pournelle Jerry # 19990915 - 8 n 1965 Dune Herbert Frank # # The fields up until the title are whitespace-separated, the rest have # to be separated with tabs (since they can contain spaces). Blank # lines and comments are skipped. my %Type = ( b => 'bio', h => 'humor', x => 'nonfic', g => 'comic', n => 'novel', s => 'shortfic', o => 'other', ); my %Rating = ( '' => -5, # amount applied to rescale regular ratings 'a' => -6, '-' => -7, ); use RS::Handy qw(data_dump inverse_hash xdie); my $Debug = 0; my $Exit = 0; my %Rating_rev = inverse_hash %Rating; my @Head = ('-s', '', '-r', '-y', '-d', '-t', '-a'); my %Link = ( '-s' => 'Started', '' => 'Finished', '-r' => 'Rating', '-y' => 'Type', '-d' => 'Copyright', '-t' => 'Title', '-a' => 'Author', ); sub F_START () { 0 } sub F_END () { 1 } sub F_RATING () { 2 } sub F_TYPE () { 3 } sub F_COPYRIGHT () { 4 } sub F_TITLE () { 5 } sub F_AUTHOR () { 6 } sub xwarn { RS::Handy::xwarn @_; $Exit ||= 1; } sub preamble { print <<EOF <html><head><title>Books I've Read

#!/usr/bin/perl -w use strict; # $Id: books-gen,v 1.16 2006-12-21 21:48:05-05 roderick Exp $ # # Roderick Schertler # Copyright (C) 1999 Roderick Schertler # # This program is free software; you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by # the Free Software Foundation; either version 2 of the License, or (at # your option) any later version. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU # General Public License for more details. # # For a copy of the GNU General Public License write to the Free Software # Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA # This program converts my text-file database of books read to HTML # pages. Input data (read with <>) is in the form # # start-date end-date \ # <tab><author>[<tab><author>]... # # eg # # - 19891228 - n ---- The Golden Apple Shea R. Wilson R. A. # - 19920516 2 n 1972 A Transatlantic Tunnel Hurrah! Harrison Harry # 19950717 19950726 7 n 1974 The Mote in God's Eye Niven Larry Pournelle Jerry # 19990915 - 8 n 1965 Dune Herbert Frank # # The fields up until the title are whitespace-separated, the rest have # to be separated with tabs (since they can contain spaces). Blank # lines and comments are skipped. my %Type = ( b => 'bio', h => 'humor', x => 'nonfic', g => 'comic', n => 'novel', s => 'shortfic', o => 'other', ); my %Rating = ( '' => -5, # amount applied to rescale regular ratings 'a' => -6, '-' => -7, ); use RS::Handy qw(data_dump inverse_hash xdie); my $Debug = 0; my $Exit = 0; my %Rating_rev = inverse_hash %Rating; my @Head = ('-s', '', '-r', '-y', '-d', '-t', '-a'); my %Link = ( '-s' => 'Started', '' => 'Finished', '-r' => 'Rating', '-y' => 'Type', '-d' => 'Copyright', '-t' => 'Title', '-a' => 'Author', ); sub F_START () { 0 } sub F_END () { 1 } sub F_RATING () { 2 } sub F_TYPE () { 3 } sub F_COPYRIGHT () { 4 } sub F_TITLE () { 5 } sub F_AUTHOR () { 6 } sub xwarn { RS::Handy::xwarn @_; $Exit ||= 1; } sub preamble { print <<EOF <html><head><title>Books I've Read

Back to index

Here's a list of most of the non-technical books I've read since 1990.

Rating: 0 is an average enjoyable read, positive is better than average and negative is worse. "a" (for abandoned) is a book I chose not to finish. I didn't start out with strict guidelines for the scale, but I've never gone over +3 or under -3. I have a lot more positive ratings than negative, I've presumed this is because I'm unlikely to pick up a book which I don't think I'll like.
If you largely agree with my rankings and you know a +2 or better which isn't on my list, tell me about it!
Copyright: I'd prefer to track when the book was written, but I don't have a good way to do that. I settled on tracking copyright dates in most cases.

EOF } sub postamble { print < These HTML pages are generated from a text file using my books-gen script.

Roderick Schertler <roderick\@argon.org>

Back to index EOF } sub parse { my @book; while (<>) { s/^\s*#.*//; next if /^\s*$/; chomp; my ($start, $end, $rating, $type, $copyright, $rest) = split ' ', $_, 6; my ($title, @author) = split /\t+/, $rest; defined $author[0] or xdie "no author"; if ($start eq '-') { $start = ''; } else { $start =~ /^(\d\d\d\d)(\d\d)(\d\d)$/ or xdie "invalid start `$start'"; $start = "$1-$2-$3"; } if ($end eq '-') { $end = ''; } else { $end =~ /^(\d\d\d\d)(\d\d)(\d\d)$/ or xdie "invalid end `$end'"; $end = "$1-$2-$3"; } if (defined(my $new = $Rating{$rating})) { $rating = $new; } elsif ($rating =~ /^\d$/) { $rating += $Rating{''}; } else { xdie "invalid rating `$rating'"; } if (!defined $Type{$type}) { xdie "invalid type `$type'"; } if ($copyright =~ /^-+$/) { $copyright = '-1'; } elsif ($copyright !~ /^\d{4}$/) { xdie "invalid copyright `$copyright'"; } push @book, [$start, $end, $rating, $type, $copyright, $title, \@author]; } return @book; } sub page_file { my ($type) = @_; return "books$type.html"; } sub header { my ($type) = @_; my $saw_type; print ""; for (@Head) { if ($type eq $_) { print " $Link{$_}"; $saw_type = 1; } else { print ' $Link{$_}"; } } $saw_type or xdie "invalid type `$type'\n"; } sub table { my ($type, @book) = @_; print "

\n"; header $type; for (@book) { my ($start, $end, $rating, $type, $copyright, $title, $rauthor) = @$_; $start = ' ' if $start eq ''; $end = ' ' if $end eq ''; if (defined(my $new = $Rating_rev{$rating})) { $rating = $new; } $type = $Type{$type}; $copyright = ' ' if $copyright == -1; my $author = join '
', @$rauthor; print "", "
$start", " $end", " $rating", " $type", " $copyright", " $title $author\n"; } header $type; print "
\n"; } sub page { my ($type, @book) = @_; local *FILE; my $file = page_file $type; print "generating $file\n"; open FILE, ">$file" or xdie "can't create $file:"; my $old_fh = select FILE; preamble; table $type, @book; postamble; close FILE or xdie "error closing $file:"; select $old_fh; } { my %cache; sub dict ($) { my $s =shift; $cache{$s} ||= do { $s = lc $s; $s =~ tr/'//d; $s =~ tr/a-z/ /cs; $s =~ s/^ //; $s =~ s/ $//; $s =~ s/^(a|an|the) //; #print "$s\n"; $s } } } sub main { my @book = parse; page '', reverse @book; page '-s', @book[sort { $book[$b][F_START] cmp $book[$a][F_START] or $b <=> $a } 0..$#book]; page '-r', @book[sort { $book[$b][F_RATING] <=> $book[$a][F_RATING] or $b <=> $a } 0..$#book]; page '-y', @book[sort { $book[$a][F_TYPE] cmp $book[$b][F_TYPE] or $b <=> $a } 0..$#book]; page '-d', @book[sort { $book[$b][F_COPYRIGHT] <=> $book[$a][F_COPYRIGHT] or $b <=> $a } 0..$#book]; page '-t', @book[sort { dict $book[$a][F_TITLE] cmp dict $book[$b][F_TITLE] or $b <=> $a } 0..$#book]; # For the author sort, create a separate entry for each author of a # book. my @author; for my $b (@book) { my @a = @{ $b->[F_AUTHOR] }; for (my $i = 0; $i <= $#a; $i++) { push @author, [@$b]; # Rearrange the author list so this author comes first. $author[$#author][F_AUTHOR] = [@a]; unshift @{ $author[$#author][F_AUTHOR] }, splice @{ $author[$#author][F_AUTHOR] }, $i, 1; } } page '-a', @author[sort { $author[$a][F_AUTHOR][0] cmp $author[$b][F_AUTHOR][0] or $b <=> $a } 0..$#author]; return 0; } $Exit = main || $Exit; $Exit = 1 if $Exit && !($Exit % 256); exit $Exit; # XXX add histograms for ratings, count by year, others?