X-Git-Url: http://jaekl.net/gitweb/?p=quanlib.git;a=blobdiff_plain;f=book.rb;h=6d90c0e2947a0a243b3480758518159e075d8d85;hp=e0ccc841eed4c86600d56e18b0373fc14a138ab2;hb=HEAD;hpb=fcaeedd4d1c128ff84371c0a7db5d0af6751492a
diff --git a/book.rb b/book.rb
index e0ccc84..2b93f4b 100644
--- a/book.rb
+++ b/book.rb
@@ -1,26 +1,33 @@
require 'nokogiri'
+require 'rubygems'
require 'zip'
-require 'author'
-require 'cover'
-require 'store'
+require_relative 'author'
+require_relative 'classification'
+require_relative 'cover'
+require_relative 'store'
class Book
@@DC_NS_URL = 'http://purl.org/dc/elements/1.1/'
+ @@SERIES_AND_VOLUME_REGEX = /^([A-Z]+)([0-9]+(\.[0-9]+)?)$/
+
+ attr_accessor :arrived
+ attr_accessor :author
+ attr_accessor :classification_id
+ attr_accessor :cover
+ attr_accessor :description
+ attr_accessor :language
+ attr_accessor :path
+ attr_accessor :series_id
+ attr_accessor :title
+ attr_accessor :volume
def initialize(store)
- @author = nil
- @cover = nil
- @description = nil
- @path = nil
- @series_id = nil
@store = store
- @title = nil
- @volume = nil
end
- def load_from_file(fileName)
+ def load_from_file!(fileName)
@path = fileName
parse_file_name!(fileName)
end
@@ -44,28 +51,16 @@ class Book
return false
end
- def author
- return @author
- end
-
- def author=(value)
- @author = value
- end
-
- def cover
- return @cover
- end
-
- def cover=(value)
- @cover = value
- end
+ def self.grouping_for_title(title)
+ result = title
- def description
- @description
- end
+ '\'",!#'.split('').each do |c|
+ result = result.gsub(c, '-')
+ end
+ result = result.gsub(/: */, '--')
+ result = result.gsub(' ', '_')
- def description=(value)
- @description = value
+ result
end
def heading
@@ -79,7 +74,7 @@ class Book
if nil != @author
result.push('by ' + @author.reading_order + '')
end
-
+
seriesInfo = []
series = @store.load_series(@series_id)
if nil != series and nil != series.descr
@@ -92,6 +87,19 @@ class Book
result.push(seriesInfo.join(' '))
end
+ classification = nil
+ if nil != @classification_id
+ classification = @store.load_classification(@classification_id)
+ end
+ if nil != classification
+ if nil != classification.ddc
+ result.push('Dewey: ' + classification.ddc.to_s)
+ end
+ if nil != classification.lcc
+ result.push('LCC: ' + classification.lcc.to_s)
+ end
+ end
+
return result.join('
')
end
@@ -118,40 +126,16 @@ class Book
return '(Book:' + data.join(',') + ')'
end
- def path
- @path
- end
-
- def path=(value)
- @path = value
- end
-
- def series_id
- @series_id
- end
-
- def series_id=(value)
- @series_id = value
- end
-
def to_s
return inspect()
end
- def title
- @title
- end
-
- def title=(value)
- @title = value
- end
-
- def volume
- @volume
- end
+ def title_grouping
+ if nil == @path
+ return nil
+ end
- def volume=(value)
- @volume = value
+ return File.basename(@path, '.*')
end
protected
@@ -189,7 +173,7 @@ class Book
vol = nil
first = arr[0]
- matchData = (arr[0]).match(/^([A-Z]+)([0-9]+)$/)
+ matchData = (arr[0]).match(@@SERIES_AND_VOLUME_REGEX)
if nil != matchData
capt = matchData.captures
series = capt[0]
@@ -204,11 +188,23 @@ class Book
title = arr.join(' ')
+ bare_title_grouping = title_grouping
+ .split('_')
+ .reject { |part| part.match(@@SERIES_AND_VOLUME_REGEX) }
+ .join('_')
+
+ unless bare_title_grouping == Book.grouping_for_title(title)
+ puts "WARNING: title_grouping mismatch: #{bare_title_grouping.inspect} vs. #{Book.grouping_for_title(title).inspect}"
+ end
+
return series, vol, title
end
protected
def parse_file_name!(file_name)
+ category = nil # e.g., non-fiction, fan-fiction
+ grouping = ''
+
parts = file_name.split('/')
(series_code, @volume, @title) = processTitle(parts[-1])
if parts.length > 1
@@ -218,6 +214,9 @@ class Book
@author = Author.new(grouping, reading_order, sort_order)
@series_id = @store.get_series(grouping, series_code)
end
+ if parts.length > 2
+ category = parts[-3]
+ end
lc_file_name = file_name.downcase
if lc_file_name.end_with?(".epub")
@@ -225,12 +224,24 @@ class Book
elsif lc_file_name.end_with?(".pdf")
scan_pdf!(file_name)
end
+
+ @arrived = File.ctime(file_name)
+
+ @classification_id = @store.find_classification(@author.grouping, File.basename(file_name, '.*'))
+
+ # TODO: Fix horrible hard-coded strings and paths
+ if ('01_nonfic' == category) && (nil == classification_id)
+ open(Store.unclassified_csv, 'a') do |fd|
+ fd.puts('"' + grouping.to_s + '","' + path + '"')
+ end
+ end
end
- protected
+ protected
def scanEpub!(fileName)
#puts 'Scanning "' + fileName.to_s + '"...'
begin
+ Zip.warn_invalid_date = false
Zip::File.open(fileName) do |zipfile|
entry = zipfile.find_entry('META-INF/container.xml')
if nil == entry
@@ -314,7 +325,7 @@ class Book
#---------------------------------------
# Description
-
+
descrNodes = opfDoc.css('dc|description', 'dc' => @@DC_NS_URL)
if (descrNodes.length > 0)
descrNode = descrNodes[0]
@@ -323,6 +334,17 @@ class Book
end
end
+ #---------------------------------------
+ # Language
+
+ langNodes = opfDoc.css('dc|language', 'dc' => @@DC_NS_URL)
+ if (langNodes.length > 0)
+ langNode = langNodes[0]
+ if langNode
+ @language = langNode.content
+ end
+ end
+
#---------------------------------------
# Other metadata: series, volume, cover
@@ -365,9 +387,9 @@ class Book
entry = zipfile.find_entry(href)
if nil == entry
- # Although the epub standard requires the path to be relative
+ # Although the epub standard requires the path to be relative
# to the base of the epub (zip), some books encountered in the
- # wild have been found to use a bath relative to the location
+ # wild have been found to use a bath relative to the location
# of the opf file.
parts = opfPath.split('/')
opfBasePath = opfPath.split('/')[0..-2].join('/')
@@ -375,6 +397,14 @@ class Book
entry = zipfile.find_entry(coverPath)
end
+ unless entry
+ # Another case found in the wild: cover image is at the root, but path is '../cover.jpeg'
+ if href.start_with? '../'
+ coverPath = href[3..-1]
+ entry = zipfile.find_entry(coverPath)
+ end
+ end
+
if nil == entry
puts 'WARNING! Cover image "' + href + '" not found in file "' + @path + '".'
return nil