cacofonix 0.10.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +2 -0
- data/.rvmrc +1 -0
- data/.travis.yml +10 -0
- data/CHANGELOG.md +205 -0
- data/CODE_OF_CONDUCT.md +74 -0
- data/Gemfile +5 -0
- data/LICENSE.txt +22 -0
- data/README.md +76 -0
- data/Rakefile +6 -0
- data/TODO +14 -0
- data/bin/onix_extract_codelists +41 -0
- data/cacofonix.gemspec +39 -0
- data/data/9780194351898.xml +74 -0
- data/data/Ashgate Other.xml +382679 -0
- data/data/Bookwise_July_2008.xml +21611 -0
- data/data/Peribo Onix 0408.xml +17051 -0
- data/data/aau.xml +96 -0
- data/data/audience_range.xml +9 -0
- data/data/contributor.xml +6 -0
- data/data/control_chars.xml +74 -0
- data/data/entities.xml +78 -0
- data/data/extra_entities.xml +65 -0
- data/data/header.xml +21 -0
- data/data/header_invalid_sentdate.xml +21 -0
- data/data/hlasep08.xml +24519 -0
- data/data/imprint.xml +5 -0
- data/data/iso_8859_1.xml +58 -0
- data/data/jul.xml +24783 -0
- data/data/language.xml +7 -0
- data/data/market_representation.xml +11 -0
- data/data/measure.xml +6 -0
- data/data/media_file.xml +6 -0
- data/data/no_encoding.xml +78 -0
- data/data/no_xml_declaration.xml +95 -0
- data/data/other_text.xml +5 -0
- data/data/price.xml +5 -0
- data/data/product.xml +79 -0
- data/data/product_identifier.xml +5 -0
- data/data/product_invalid_pubdate.xml +42 -0
- data/data/publisher.xml +5 -0
- data/data/rba_FANT.xml +23 -0
- data/data/reference_with_release_attrib.xml +74 -0
- data/data/sales_restriction.xml +4 -0
- data/data/sales_rights.xml +35 -0
- data/data/sender_identifier.xml +5 -0
- data/data/series.xml +5 -0
- data/data/series_identifier.xml +6 -0
- data/data/short_tags.xml +191 -0
- data/data/short_tags_ivp.xml +231 -0
- data/data/sl_product.xml +81 -0
- data/data/stock.xml +5 -0
- data/data/subject.xml +6 -0
- data/data/supply_detail.xml +18 -0
- data/data/title.xml +6 -0
- data/data/two_products.xml +114 -0
- data/data/usd.xml +175 -0
- data/data/utf_16.xml +0 -0
- data/data/website.xml +6 -0
- data/examples/reader.rb +25 -0
- data/examples/reader_apa.rb +22 -0
- data/examples/writer.rb +13 -0
- data/examples/writer_apa.rb +38 -0
- data/lib/cacofonix.rb +151 -0
- data/lib/cacofonix/codelists/001.rb +16 -0
- data/lib/cacofonix/codelists/002.rb +11 -0
- data/lib/cacofonix/codelists/003.rb +13 -0
- data/lib/cacofonix/codelists/005.rb +20 -0
- data/lib/cacofonix/codelists/006.rb +82 -0
- data/lib/cacofonix/codelists/007.rb +129 -0
- data/lib/cacofonix/codelists/008.rb +13 -0
- data/lib/cacofonix/codelists/009.rb +13 -0
- data/lib/cacofonix/codelists/010.rb +52 -0
- data/lib/cacofonix/codelists/011.rb +17 -0
- data/lib/cacofonix/codelists/012.rb +17 -0
- data/lib/cacofonix/codelists/013.rb +13 -0
- data/lib/cacofonix/codelists/014.rb +10 -0
- data/lib/cacofonix/codelists/015.rb +19 -0
- data/lib/cacofonix/codelists/016.rb +12 -0
- data/lib/cacofonix/codelists/017.rb +96 -0
- data/lib/cacofonix/codelists/018.rb +11 -0
- data/lib/cacofonix/codelists/019.rb +13 -0
- data/lib/cacofonix/codelists/020.rb +7 -0
- data/lib/cacofonix/codelists/021.rb +39 -0
- data/lib/cacofonix/codelists/022.rb +15 -0
- data/lib/cacofonix/codelists/023.rb +19 -0
- data/lib/cacofonix/codelists/024.rb +17 -0
- data/lib/cacofonix/codelists/025.rb +35 -0
- data/lib/cacofonix/codelists/026.rb +86 -0
- data/lib/cacofonix/codelists/027.rb +90 -0
- data/lib/cacofonix/codelists/028.rb +14 -0
- data/lib/cacofonix/codelists/029.rb +25 -0
- data/lib/cacofonix/codelists/030.rb +22 -0
- data/lib/cacofonix/codelists/031.rb +9 -0
- data/lib/cacofonix/codelists/032.rb +8 -0
- data/lib/cacofonix/codelists/033.rb +43 -0
- data/lib/cacofonix/codelists/034.rb +21 -0
- data/lib/cacofonix/codelists/035.rb +12 -0
- data/lib/cacofonix/codelists/036.rb +9 -0
- data/lib/cacofonix/codelists/037.rb +12 -0
- data/lib/cacofonix/codelists/038.rb +43 -0
- data/lib/cacofonix/codelists/039.rb +14 -0
- data/lib/cacofonix/codelists/040.rb +12 -0
- data/lib/cacofonix/codelists/041.rb +12 -0
- data/lib/cacofonix/codelists/042.rb +22 -0
- data/lib/cacofonix/codelists/043.rb +12 -0
- data/lib/cacofonix/codelists/044.rb +22 -0
- data/lib/cacofonix/codelists/045.rb +19 -0
- data/lib/cacofonix/codelists/046.rb +15 -0
- data/lib/cacofonix/codelists/047.rb +10 -0
- data/lib/cacofonix/codelists/048.rb +17 -0
- data/lib/cacofonix/codelists/049.rb +91 -0
- data/lib/cacofonix/codelists/050.rb +14 -0
- data/lib/cacofonix/codelists/051.rb +36 -0
- data/lib/cacofonix/codelists/052.rb +7 -0
- data/lib/cacofonix/codelists/053.rb +10 -0
- data/lib/cacofonix/codelists/054.rb +29 -0
- data/lib/cacofonix/codelists/055.rb +23 -0
- data/lib/cacofonix/codelists/056.rb +8 -0
- data/lib/cacofonix/codelists/057.rb +11 -0
- data/lib/cacofonix/codelists/058.rb +29 -0
- data/lib/cacofonix/codelists/059.rb +13 -0
- data/lib/cacofonix/codelists/060.rb +8 -0
- data/lib/cacofonix/codelists/061.rb +9 -0
- data/lib/cacofonix/codelists/062.rb +11 -0
- data/lib/cacofonix/codelists/063.rb +7 -0
- data/lib/cacofonix/codelists/064.rb +19 -0
- data/lib/cacofonix/codelists/065.rb +34 -0
- data/lib/cacofonix/codelists/066.rb +10 -0
- data/lib/cacofonix/codelists/067.rb +8 -0
- data/lib/cacofonix/codelists/068.rb +22 -0
- data/lib/cacofonix/codelists/069.rb +10 -0
- data/lib/cacofonix/codelists/070.rb +8 -0
- data/lib/cacofonix/codelists/071.rb +16 -0
- data/lib/cacofonix/codelists/072.rb +13 -0
- data/lib/cacofonix/codelists/073.rb +42 -0
- data/lib/cacofonix/codelists/074.rb +495 -0
- data/lib/cacofonix/codelists/075.rb +8 -0
- data/lib/cacofonix/codelists/076.rb +18 -0
- data/lib/cacofonix/codelists/077.rb +25 -0
- data/lib/cacofonix/codelists/078.rb +173 -0
- data/lib/cacofonix/codelists/079.rb +25 -0
- data/lib/cacofonix/codelists/080.rb +26 -0
- data/lib/cacofonix/codelists/081.rb +45 -0
- data/lib/cacofonix/codelists/082.rb +23 -0
- data/lib/cacofonix/codelists/083.rb +74 -0
- data/lib/cacofonix/codelists/084.rb +16 -0
- data/lib/cacofonix/codelists/085.rb +29 -0
- data/lib/cacofonix/codelists/086.rb +11 -0
- data/lib/cacofonix/codelists/087.rb +12 -0
- data/lib/cacofonix/codelists/088.rb +7 -0
- data/lib/cacofonix/codelists/089.rb +7 -0
- data/lib/cacofonix/codelists/090.rb +17 -0
- data/lib/cacofonix/codelists/091.rb +257 -0
- data/lib/cacofonix/codelists/092.rb +14 -0
- data/lib/cacofonix/codelists/093.rb +19 -0
- data/lib/cacofonix/codelists/094.rb +9 -0
- data/lib/cacofonix/codelists/095.rb +9 -0
- data/lib/cacofonix/codelists/096.rb +191 -0
- data/lib/cacofonix/codelists/097.rb +7 -0
- data/lib/cacofonix/codelists/098.rb +27 -0
- data/lib/cacofonix/codelists/099.rb +30 -0
- data/lib/cacofonix/codelists/100.rb +12 -0
- data/lib/cacofonix/codelists/101.rb +8 -0
- data/lib/cacofonix/codelists/102.rb +9 -0
- data/lib/cacofonix/codelists/121.rb +164 -0
- data/lib/cacofonix/codelists/138.rb +12 -0
- data/lib/cacofonix/codelists/139.rb +76 -0
- data/lib/cacofonix/codelists/140.rb +13 -0
- data/lib/cacofonix/codelists/141.rb +16 -0
- data/lib/cacofonix/codelists/142.rb +18 -0
- data/lib/cacofonix/codelists/143.rb +13 -0
- data/lib/cacofonix/codelists/144.rb +12 -0
- data/lib/cacofonix/codelists/145.rb +13 -0
- data/lib/cacofonix/codelists/146.rb +9 -0
- data/lib/cacofonix/codelists/147.rb +16 -0
- data/lib/cacofonix/codelists/148.rb +9 -0
- data/lib/cacofonix/codelists/149.rb +10 -0
- data/lib/cacofonix/codelists/150.rb +130 -0
- data/lib/cacofonix/codelists/151.rb +13 -0
- data/lib/cacofonix/codelists/152.rb +8 -0
- data/lib/cacofonix/codelists/153.rb +20 -0
- data/lib/cacofonix/codelists/154.rb +15 -0
- data/lib/cacofonix/codelists/155.rb +11 -0
- data/lib/cacofonix/codelists/156.rb +10 -0
- data/lib/cacofonix/codelists/157.rb +10 -0
- data/lib/cacofonix/codelists/158.rb +32 -0
- data/lib/cacofonix/codelists/159.rb +12 -0
- data/lib/cacofonix/codelists/160.rb +10 -0
- data/lib/cacofonix/codelists/161.rb +9 -0
- data/lib/cacofonix/codelists/162.rb +12 -0
- data/lib/cacofonix/codelists/163.rb +17 -0
- data/lib/cacofonix/codelists/164.rb +11 -0
- data/lib/cacofonix/codelists/165.rb +9 -0
- data/lib/cacofonix/codelists/166.rb +9 -0
- data/lib/cacofonix/codelists/167.rb +9 -0
- data/lib/cacofonix/codelists/168.rb +8 -0
- data/lib/cacofonix/codelists/169.rb +9 -0
- data/lib/cacofonix/codelists/170.rb +7 -0
- data/lib/cacofonix/codelists/171.rb +8 -0
- data/lib/cacofonix/codelists/172.rb +7 -0
- data/lib/cacofonix/codelists/173.rb +8 -0
- data/lib/cacofonix/codelists/174.rb +8 -0
- data/lib/cacofonix/codelists/175.rb +206 -0
- data/lib/cacofonix/codelists/176.rb +20 -0
- data/lib/cacofonix/codelists/177.rb +8 -0
- data/lib/cacofonix/codelists/178.rb +24 -0
- data/lib/cacofonix/codelists/179.rb +7 -0
- data/lib/cacofonix/codelists/184.rb +11 -0
- data/lib/cacofonix/core/code.rb +106 -0
- data/lib/cacofonix/core/element.rb +275 -0
- data/lib/cacofonix/core/header.rb +45 -0
- data/lib/cacofonix/core/lists.rb +108 -0
- data/lib/cacofonix/core/reader.rb +166 -0
- data/lib/cacofonix/core/writer.rb +123 -0
- data/lib/cacofonix/elements/addressee_identifier.rb +6 -0
- data/lib/cacofonix/elements/agent_identifier.rb +6 -0
- data/lib/cacofonix/elements/audience.rb +8 -0
- data/lib/cacofonix/elements/audience_range.rb +15 -0
- data/lib/cacofonix/elements/batch_bonus.rb +7 -0
- data/lib/cacofonix/elements/bible.rb +12 -0
- data/lib/cacofonix/elements/complexity.rb +7 -0
- data/lib/cacofonix/elements/conference.rb +14 -0
- data/lib/cacofonix/elements/conference_sponsor.rb +8 -0
- data/lib/cacofonix/elements/conference_sponsor_identifier.rb +6 -0
- data/lib/cacofonix/elements/contained_item.rb +6 -0
- data/lib/cacofonix/elements/content_item.rb +21 -0
- data/lib/cacofonix/elements/contributor.rb +19 -0
- data/lib/cacofonix/elements/copyright_owner.rb +8 -0
- data/lib/cacofonix/elements/copyright_owner_identifier.rb +6 -0
- data/lib/cacofonix/elements/copyright_statement.rb +7 -0
- data/lib/cacofonix/elements/discount_coded.rb +8 -0
- data/lib/cacofonix/elements/extent.rb +8 -0
- data/lib/cacofonix/elements/identifier.rb +7 -0
- data/lib/cacofonix/elements/illustrations.rb +8 -0
- data/lib/cacofonix/elements/imprint.rb +9 -0
- data/lib/cacofonix/elements/language.rb +8 -0
- data/lib/cacofonix/elements/location_identifier.rb +8 -0
- data/lib/cacofonix/elements/main_subject.rb +9 -0
- data/lib/cacofonix/elements/market_date.rb +8 -0
- data/lib/cacofonix/elements/market_representation.rb +18 -0
- data/lib/cacofonix/elements/measure.rb +8 -0
- data/lib/cacofonix/elements/media_file.rb +16 -0
- data/lib/cacofonix/elements/name.rb +6 -0
- data/lib/cacofonix/elements/name_base.rb +17 -0
- data/lib/cacofonix/elements/new_supplier.rb +12 -0
- data/lib/cacofonix/elements/not_for_sale.rb +13 -0
- data/lib/cacofonix/elements/on_order_detail.rb +7 -0
- data/lib/cacofonix/elements/other_text.rb +17 -0
- data/lib/cacofonix/elements/page_run.rb +7 -0
- data/lib/cacofonix/elements/person_date.rb +8 -0
- data/lib/cacofonix/elements/person_name_identifier.rb +6 -0
- data/lib/cacofonix/elements/price.rb +46 -0
- data/lib/cacofonix/elements/prize.rb +10 -0
- data/lib/cacofonix/elements/product.rb +155 -0
- data/lib/cacofonix/elements/product_base.rb +61 -0
- data/lib/cacofonix/elements/product_classification.rb +8 -0
- data/lib/cacofonix/elements/product_form_feature.rb +8 -0
- data/lib/cacofonix/elements/product_identifier.rb +6 -0
- data/lib/cacofonix/elements/professional_affiliation.rb +7 -0
- data/lib/cacofonix/elements/publisher.rb +11 -0
- data/lib/cacofonix/elements/reissue.rb +9 -0
- data/lib/cacofonix/elements/related_product.rb +6 -0
- data/lib/cacofonix/elements/religious_text.rb +8 -0
- data/lib/cacofonix/elements/religious_text_feature.rb +8 -0
- data/lib/cacofonix/elements/sales_outlet.rb +7 -0
- data/lib/cacofonix/elements/sales_outlet_identifier.rb +6 -0
- data/lib/cacofonix/elements/sales_restriction.rb +7 -0
- data/lib/cacofonix/elements/sales_rights.rb +13 -0
- data/lib/cacofonix/elements/sender_identifier.rb +6 -0
- data/lib/cacofonix/elements/series.rb +11 -0
- data/lib/cacofonix/elements/series_identifier.rb +6 -0
- data/lib/cacofonix/elements/set.rb +13 -0
- data/lib/cacofonix/elements/stock.rb +16 -0
- data/lib/cacofonix/elements/stock_quantity_coded.rb +8 -0
- data/lib/cacofonix/elements/subject.rb +13 -0
- data/lib/cacofonix/elements/supplier_identifier.rb +6 -0
- data/lib/cacofonix/elements/supply_detail.rb +37 -0
- data/lib/cacofonix/elements/text_item.rb +11 -0
- data/lib/cacofonix/elements/text_item_identifier.rb +6 -0
- data/lib/cacofonix/elements/title.rb +11 -0
- data/lib/cacofonix/elements/website.rb +8 -0
- data/lib/cacofonix/elements/work_identifier.rb +6 -0
- data/lib/cacofonix/utils/code_list_extractor.rb +112 -0
- data/lib/cacofonix/utils/normaliser.rb +125 -0
- data/lib/cacofonix/version.rb +5 -0
- data/lib/cacofonix/wrappers/apa_product.rb +748 -0
- data/lib/cacofonix/wrappers/simple_product.rb +49 -0
- data/support/entities.txt +1499 -0
- data/support/extract.rb +25 -0
- data/support/switch-onix-2.1-short-to-reference.xsl +24 -0
- data/support/switch-onix-tagnames-1.1.xsl +25 -0
- data/support/switch-onix-tagnames-2.0.xsl +37 -0
- metadata +438 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA256:
|
3
|
+
metadata.gz: 7d71358bce0d5d281f6d8ea181ea0a8b50ea74acd5b5df2e6079d2ab4d98a6fe
|
4
|
+
data.tar.gz: b1802248185109acad0b4cf4951fc701bbb841fc38dc3935da5e519e5db70148
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 335a075c708ad440c71554dc03ef92201dd797dad92ef9d6ac29f729ebdfc4ca46022b6111a325834acecc69d169645b2f512c86a7b1cd9f465b15ab98a32eb4
|
7
|
+
data.tar.gz: aae5a765f88eaa478b7bce6c9590f4900922f778d298ab8de47c605f8225cd74cf7ddfd6f1e29dcc6ca1ddb5719dd3351ddbcda3cd52dd2e011da67f2670f644
|
data/.gitignore
ADDED
data/.rvmrc
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
rvm use ree@onix
|
data/.travis.yml
ADDED
data/CHANGELOG.md
ADDED
@@ -0,0 +1,205 @@
|
|
1
|
+
# Changelog
|
2
|
+
|
3
|
+
## [0.10.0] - 2019-07-08
|
4
|
+
|
5
|
+
### Changed
|
6
|
+
|
7
|
+
- Rename gem from onix to cacofonix
|
8
|
+
- Rename primary module namespace from `ONIX` to `Cacofonix`
|
9
|
+
- Use Cacofonix::DTDs to set appropriate env vars before XML parsing; required for ONIX 2.1 DTDs to be properly loaded and related entities in source XML files to be respected
|
10
|
+
- Address Fixnum->Integer and BigDecimal.new->BigDecimal deprecations
|
11
|
+
- Require Ruby 2.5 or newer
|
12
|
+
|
13
|
+
# Previous releases (as onix gem)
|
14
|
+
|
15
|
+
v0.9.1 (5th September 2011)
|
16
|
+
- relax activesupport dependency to work with rails 3 or 3.1
|
17
|
+
|
18
|
+
v0.9.0 (14th April 2011)
|
19
|
+
- switch back to the vanilla roxml gem. Ben is maintaining it again and
|
20
|
+
he has merged in my bug fixes
|
21
|
+
- clarify comments explaining encoding behaviour
|
22
|
+
- Add options hash to ONIX::Reader. Only option at this stage is :encoding,
|
23
|
+
which allows the user to override the assumed encoding of the input XML
|
24
|
+
- API change, so new minor version
|
25
|
+
|
26
|
+
v0.8.5 (21st December 2010)
|
27
|
+
- update packaging - use bundler and rspec 2.x
|
28
|
+
- support normalising short tag files that include HTML tags
|
29
|
+
|
30
|
+
v0.8.4 (18th October 2010)
|
31
|
+
- some small fixes to xml names from Tim
|
32
|
+
- make all code lists available via the ONIX::Lists class
|
33
|
+
|
34
|
+
v0.8.3 (9th September 2010)
|
35
|
+
- Fix for race condition in ONIX::Normaliser
|
36
|
+
- thanks to pixelvixen for reporting
|
37
|
+
- force roxml to be 3.1.6 or higher. Earlier versions misbehaved when monkey
|
38
|
+
patching nokogiri
|
39
|
+
|
40
|
+
v0.8.2 (6th May 2010)
|
41
|
+
- fix APAProduct#series and APAProduct#series=
|
42
|
+
|
43
|
+
v0.8.1 (5th January 2010)
|
44
|
+
- Use nokogiri's support for transparent entity conversion when reading an ONIX file
|
45
|
+
- Removed entity replacement from ONIX::Normaliser
|
46
|
+
- the external dependency on sed made me uncomfortable, and it wasn't really
|
47
|
+
necessary now that nokogiri can do it for us
|
48
|
+
- Removed utf-8 normalisation from ONIX::Normaliser
|
49
|
+
- nokogiri also handles this really cleanly and transparently. Regardless of
|
50
|
+
the source file encoding, Nokogiri::Reader returns utf-8 encoded data
|
51
|
+
- Add the release attribute to files we generate
|
52
|
+
- it's optional in 2.1, but mandatory in 3.0. As we start to see 3.0 files in the
|
53
|
+
wild it will help to have a rapid way to distinguish between them
|
54
|
+
- Add ONIX::Reader#release - to detect the release version of files we read in
|
55
|
+
|
56
|
+
v0.8.0 (31st October 2009)
|
57
|
+
- Replace LibXML dependency with Nokogiri. Nokogiri is under active development, has
|
58
|
+
a responsive maintainer and is significantly more stable
|
59
|
+
- Switch to ROXML 3.x
|
60
|
+
- roxml also switched from libxml to nokogiri
|
61
|
+
- roxml removed deprecated parts of it's API
|
62
|
+
- should now avoid various conflicts with mongrel
|
63
|
+
- Ensure APAProduct#price returns the first product price and ignores
|
64
|
+
the price type
|
65
|
+
|
66
|
+
v0.7.8 (19th October 2009)
|
67
|
+
- add support for additional elements (mostly series and audience related)
|
68
|
+
- thanks tim
|
69
|
+
|
70
|
+
v0.7.7 (1st October 2009)
|
71
|
+
- optimise sed usage in ONIX::Normaliser. *huge* speed improvement on
|
72
|
+
large files.
|
73
|
+
|
74
|
+
v0.7.6 (21st September 2009)
|
75
|
+
- provide access to the PackQuantity element
|
76
|
+
|
77
|
+
v0.7.5 (8th September 2009)
|
78
|
+
- Don't raise an exception on malformed dates when reading files
|
79
|
+
|
80
|
+
v0.7.4 (2nd September 2009)
|
81
|
+
- Expand ONIX::Normaliser
|
82
|
+
- strip control chars
|
83
|
+
- add encoding declaration to valid utf-8 files that aren't declared
|
84
|
+
as such
|
85
|
+
|
86
|
+
v0.7.3 (19th August 2009)
|
87
|
+
- Switch from java to xsltproc to convert short tag ONIX files
|
88
|
+
to reference tags
|
89
|
+
|
90
|
+
v0.7.2 (19th August 2009)
|
91
|
+
- Added ONIX::Normaliser class
|
92
|
+
- for normalising various ONIX files into a form that makes them easy
|
93
|
+
to process. Shouldn't be necesary to pre-process files like this, but
|
94
|
+
I'm sick of trying to wrestle the libxml ruby bindings
|
95
|
+
|
96
|
+
v0.7.1 (24th June 2009)
|
97
|
+
- Small tweak to ordering of elements in the Product group
|
98
|
+
|
99
|
+
v0.7.0 (17th June 2009)
|
100
|
+
- try using LibXML for reader again
|
101
|
+
- retrieving the ONIX version of the input file is currently disabled, as
|
102
|
+
that seems to be the source of our instability
|
103
|
+
- Various Ruby 1.9 compatability tweaks
|
104
|
+
- add source file coding declarations. All source files are UTF-8
|
105
|
+
- ONIX::Reader ensures all input data is converted to UTF-8
|
106
|
+
- the ROXML based objects seem to forget the encoding when they're marshalled,
|
107
|
+
so force string based attributes *back* to UTF-8
|
108
|
+
|
109
|
+
v0.6.7 (Unreleased)
|
110
|
+
- add some accessors to the Title composite
|
111
|
+
|
112
|
+
v0.6.6 (Unreleased)
|
113
|
+
- Forget the S on an element name
|
114
|
+
|
115
|
+
v0.6.5 (Unreleased)
|
116
|
+
- Ruby 1.9 compat
|
117
|
+
|
118
|
+
v0.6.4 (Unreleased)
|
119
|
+
- Add APAProduct#price
|
120
|
+
|
121
|
+
v0.6.3(Unreleased)
|
122
|
+
- Bump ROXML dependency to 2.5.3 to get libxml-ruby 1.1.3 compatibility
|
123
|
+
|
124
|
+
v0.6.2 (Unreleased)
|
125
|
+
- Fix a small typo in APAProduct
|
126
|
+
|
127
|
+
v0.6.1 (Unreleased)
|
128
|
+
- Stopped using LibXMLs Reader class as the basis for our reader.
|
129
|
+
- We were getting too many segfaults (even 1 is too many!)
|
130
|
+
- until we resolve it, reverted to manual string parsing
|
131
|
+
- This is a fairly major regression of functionality. For 99% of files
|
132
|
+
it won't matter, but for some corner cases it will. ie UTF-16 encoded
|
133
|
+
files
|
134
|
+
- Will also be noticeably slower
|
135
|
+
- Hopefully only a short term fix, until I work out what is going on with
|
136
|
+
libxml
|
137
|
+
|
138
|
+
v0.6.0 (18th March 2009)
|
139
|
+
- remove use of threads in ONIX::Reader
|
140
|
+
- a producer/consumer pattern was useful in the REXML stream parsing days, but
|
141
|
+
now LibXML's Reader binding provides a better alternative
|
142
|
+
- API left unchanged, this was all under the hood
|
143
|
+
- bump required ROXML version to 2.5.2
|
144
|
+
|
145
|
+
v0.5.1 (4th March 2009)
|
146
|
+
- Fix a single letter typo
|
147
|
+
|
148
|
+
v0.5 (2nd March 2009)
|
149
|
+
- Switch ROXML dependency from a patched version to vanilla
|
150
|
+
- Vanilla ROXML now has all the features we need
|
151
|
+
- This change should be transparent to ONIX gem users
|
152
|
+
|
153
|
+
v0.4.7 (9th December 2008)
|
154
|
+
- Contributor sub elements should match the order specified in the DTD
|
155
|
+
|
156
|
+
v0.4.6 (2nd December 2008)
|
157
|
+
- 2 new accessors on the contributor class - bio and corporate name
|
158
|
+
|
159
|
+
v0.4.5 (21st November 2008)
|
160
|
+
- APAProduct wrapper should generate valid MediaFile composites
|
161
|
+
|
162
|
+
v0.4.4 (19th November 2008)
|
163
|
+
- Added support for more elements from MarketRepresentation
|
164
|
+
|
165
|
+
v0.4.3 (11th November 2008)
|
166
|
+
- Added support for AgentName and MarketPublishingStatus
|
167
|
+
|
168
|
+
v0.4.2 (1st November 2008)
|
169
|
+
- Remove final remnants of REXML code
|
170
|
+
- Minor reordering of elements to match DTD
|
171
|
+
|
172
|
+
v0.4.1 (UNRELEASED)
|
173
|
+
- Added accessors to various product measurements. Height, weight, etc.
|
174
|
+
- Reduced time for an ONIX::Reader class to initialise
|
175
|
+
|
176
|
+
v0.4.0 (28th October 2008)
|
177
|
+
- Major rework: now based on ROXML instead of xml-mapping
|
178
|
+
- Mostly API Compatible
|
179
|
+
- StreamReader and StreamWriter renamed to Reader and Writer
|
180
|
+
- ROXML is based on libxml, so things should be significantly faster
|
181
|
+
|
182
|
+
v0.2.7 (Unreleased)
|
183
|
+
- Add line breaks after each product
|
184
|
+
|
185
|
+
v0.2.5 (Unreleased)
|
186
|
+
- Make PublishingStatus a two_digit_node
|
187
|
+
|
188
|
+
v0.2.4 (Unreleased)
|
189
|
+
- Initialise the media files array of a new product correctly
|
190
|
+
|
191
|
+
v0.2.3 (Unreleased)
|
192
|
+
- Switch a few more fields over to TwoDigitNodes
|
193
|
+
- Make the product availability field accessible from APAProduct
|
194
|
+
|
195
|
+
v0.2.2 (Unreleased)
|
196
|
+
- Add a new nodetype (DateNode) for YYYYMMDD fields
|
197
|
+
|
198
|
+
v0.2.1 (Unreleased)
|
199
|
+
- Add a new nodetype (TwoDigitNode) for two digit codes
|
200
|
+
|
201
|
+
v0.2.0 (16th July 2008)
|
202
|
+
- Add support for reading and storing subject codes (BIC, BISAC, etc)
|
203
|
+
|
204
|
+
v0.1.0 (12th June 2008)
|
205
|
+
- Initial Release
|
data/CODE_OF_CONDUCT.md
ADDED
@@ -0,0 +1,74 @@
|
|
1
|
+
# Contributor Covenant Code of Conduct
|
2
|
+
|
3
|
+
## Our Pledge
|
4
|
+
|
5
|
+
In the interest of fostering an open and welcoming environment, we as
|
6
|
+
contributors and maintainers pledge to making participation in our project and
|
7
|
+
our community a harassment-free experience for everyone, regardless of age, body
|
8
|
+
size, disability, ethnicity, gender identity and expression, level of experience,
|
9
|
+
nationality, personal appearance, race, religion, or sexual identity and
|
10
|
+
orientation.
|
11
|
+
|
12
|
+
## Our Standards
|
13
|
+
|
14
|
+
Examples of behavior that contributes to creating a positive environment
|
15
|
+
include:
|
16
|
+
|
17
|
+
* Using welcoming and inclusive language
|
18
|
+
* Being respectful of differing viewpoints and experiences
|
19
|
+
* Gracefully accepting constructive criticism
|
20
|
+
* Focusing on what is best for the community
|
21
|
+
* Showing empathy towards other community members
|
22
|
+
|
23
|
+
Examples of unacceptable behavior by participants include:
|
24
|
+
|
25
|
+
* The use of sexualized language or imagery and unwelcome sexual attention or
|
26
|
+
advances
|
27
|
+
* Trolling, insulting/derogatory comments, and personal or political attacks
|
28
|
+
* Public or private harassment
|
29
|
+
* Publishing others' private information, such as a physical or electronic
|
30
|
+
address, without explicit permission
|
31
|
+
* Other conduct which could reasonably be considered inappropriate in a
|
32
|
+
professional setting
|
33
|
+
|
34
|
+
## Our Responsibilities
|
35
|
+
|
36
|
+
Project maintainers are responsible for clarifying the standards of acceptable
|
37
|
+
behavior and are expected to take appropriate and fair corrective action in
|
38
|
+
response to any instances of unacceptable behavior.
|
39
|
+
|
40
|
+
Project maintainers have the right and responsibility to remove, edit, or
|
41
|
+
reject comments, commits, code, wiki edits, issues, and other contributions
|
42
|
+
that are not aligned to this Code of Conduct, or to ban temporarily or
|
43
|
+
permanently any contributor for other behaviors that they deem inappropriate,
|
44
|
+
threatening, offensive, or harmful.
|
45
|
+
|
46
|
+
## Scope
|
47
|
+
|
48
|
+
This Code of Conduct applies both within project spaces and in public spaces
|
49
|
+
when an individual is representing the project or its community. Examples of
|
50
|
+
representing a project or community include using an official project e-mail
|
51
|
+
address, posting via an official social media account, or acting as an appointed
|
52
|
+
representative at an online or offline event. Representation of a project may be
|
53
|
+
further defined and clarified by project maintainers.
|
54
|
+
|
55
|
+
## Enforcement
|
56
|
+
|
57
|
+
Instances of abusive, harassing, or otherwise unacceptable behavior may be
|
58
|
+
reported by contacting the project team at tim(at)icelab.com.au. All
|
59
|
+
complaints will be reviewed and investigated and will result in a response that
|
60
|
+
is deemed necessary and appropriate to the circumstances. The project team is
|
61
|
+
obligated to maintain confidentiality with regard to the reporter of an incident.
|
62
|
+
Further details of specific enforcement policies may be posted separately.
|
63
|
+
|
64
|
+
Project maintainers who do not follow or enforce the Code of Conduct in good
|
65
|
+
faith may face temporary or permanent repercussions as determined by other
|
66
|
+
members of the project's leadership.
|
67
|
+
|
68
|
+
## Attribution
|
69
|
+
|
70
|
+
This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
|
71
|
+
available at [http://contributor-covenant.org/version/1/4][version]
|
72
|
+
|
73
|
+
[homepage]: http://contributor-covenant.org
|
74
|
+
[version]: http://contributor-covenant.org/version/1/4/
|
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c)
|
2
|
+
2008-2011 James Healy
|
3
|
+
2011-2012 Joseph Pearson
|
4
|
+
2019 Icelab
|
5
|
+
|
6
|
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
7
|
+
of this software and associated documentation files (the "Software"), to deal
|
8
|
+
in the Software without restriction, including without limitation the rights
|
9
|
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
10
|
+
copies of the Software, and to permit persons to whom the Software is
|
11
|
+
furnished to do so, subject to the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be included in
|
14
|
+
all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
17
|
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
18
|
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
19
|
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
20
|
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
21
|
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
22
|
+
THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,76 @@
|
|
1
|
+
# Cacofonix
|
2
|
+
|
3
|
+
Cacofonix helps you work with ONIX data in your Ruby applications. ONIX is a set
|
4
|
+
of (XML-based) standards for published products. Cacofonix focuses on the _[ONIX
|
5
|
+
for Books][onix_standard]_ standard, and currently supports ONIX 2.1 (all
|
6
|
+
revisions).
|
7
|
+
|
8
|
+
With Cacofonix, you can:
|
9
|
+
|
10
|
+
- Efficiently read ONIX files
|
11
|
+
- Map records in ONIX files to Ruby objects
|
12
|
+
- Write ONIX files
|
13
|
+
|
14
|
+
Cacofonix is an updated, maintained fork of James Healy's original [onix
|
15
|
+
gem][gem_original], also incorporating Joseph Pearson's [major
|
16
|
+
refactorings][gem_joseph] and expanded support for the standard.
|
17
|
+
|
18
|
+
[onix_standard]: https://www.editeur.org/11/Books/
|
19
|
+
[gem_original]: https://github.com/yob/onix
|
20
|
+
[gem_joseph]: https://github.com/yob/onix/pull/3
|
21
|
+
|
22
|
+
## Installation
|
23
|
+
|
24
|
+
Add this line to your application's `Gemfile`:
|
25
|
+
|
26
|
+
```ruby
|
27
|
+
gem "cacofonix"
|
28
|
+
```
|
29
|
+
|
30
|
+
And then execute:
|
31
|
+
|
32
|
+
```shell
|
33
|
+
$ bundle
|
34
|
+
```
|
35
|
+
|
36
|
+
Or install it yourself as:
|
37
|
+
|
38
|
+
```shell
|
39
|
+
$ gem install cacofonix
|
40
|
+
```
|
41
|
+
|
42
|
+
## Usage
|
43
|
+
|
44
|
+
See the files in the [examples/][examples] directory to get started quickly.
|
45
|
+
|
46
|
+
For more detail, view the comments in the following classes:
|
47
|
+
|
48
|
+
* [`Cacofonix::Reader`][reader] - For reading ONIX files
|
49
|
+
* [`Cacofonix::Writer`][writer] - For writing ONIX files
|
50
|
+
* [`Cacofonix::Normaliser`][normaliser] - For normalising ONIX files before
|
51
|
+
reading (Fixes encoding issues, etc.)
|
52
|
+
* [`Cacofonix::Lists`][lists] - For building hashes of code lists from the ONIX
|
53
|
+
spec
|
54
|
+
|
55
|
+
[examples]: examples
|
56
|
+
[reader]: lib/cacofonix/core/reader.rb
|
57
|
+
[writer]: lib/cacofonix/core/writer.rb
|
58
|
+
[normaliser]: lib/cacofonix/utils/normaliser.rb
|
59
|
+
[lists]: lib/cacofonix/core/lists.rb
|
60
|
+
|
61
|
+
## ONIX support
|
62
|
+
|
63
|
+
`Cacofonix::Reader` only handles the reference tag versions of ONIX 2.1. Use
|
64
|
+
`Cacofonix::Normaliser` to convert any short tag files to reference tags.
|
65
|
+
|
66
|
+
`Cacofonix::Writer` only generates reference tag ONIX files.
|
67
|
+
|
68
|
+
## License
|
69
|
+
|
70
|
+
The gem is available as open source under the terms of the [MIT
|
71
|
+
License](https://opensource.org/licenses/MIT).
|
72
|
+
|
73
|
+
## Code of Conduct
|
74
|
+
|
75
|
+
Everyone interacting in the Cacofonix codebase, issue trackers, chat rooms and
|
76
|
+
mailing lists is expected to follow the [code of conduct](CODE_OF_CONDUCT.md).
|
data/Rakefile
ADDED
data/TODO
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
- finish adding support for all tags in a Product record
|
2
|
+
- contributor still needs some obscure tags added
|
3
|
+
- add a new node type for dates that should be in the form YYYYMMDD
|
4
|
+
- allow symbols to be used instead of numeric codes
|
5
|
+
- contribution type, id type, etc
|
6
|
+
- validations
|
7
|
+
- hard stuff from the spec
|
8
|
+
- 2 digit numbers, 8 digit dates, char limits on text fields
|
9
|
+
- code lists
|
10
|
+
- only values in code lists allowed in relevant fields
|
11
|
+
- regional requirements
|
12
|
+
- titlepage minimum set of tags
|
13
|
+
- APA (if different to titlepage)
|
14
|
+
- documentation
|
@@ -0,0 +1,41 @@
|
|
1
|
+
#!/usr/bin/ruby
|
2
|
+
# coding: utf-8
|
3
|
+
|
4
|
+
# NB: When testing locally, you can run this as:
|
5
|
+
#
|
6
|
+
# ruby -Ilib bin/onix_extract_codelists [options] xsd dir
|
7
|
+
|
8
|
+
require 'optparse'
|
9
|
+
|
10
|
+
def parse_options
|
11
|
+
options = {}
|
12
|
+
optparse = OptionParser.new do |parser|
|
13
|
+
parser.banner = [
|
14
|
+
"Usage: onix_extract_codelists [options] xsd_path output_dir_path",
|
15
|
+
"",
|
16
|
+
" eg: onix_extract_codelists ONIX_BookProduct_CodeLists.xsd support/codes"
|
17
|
+
].join("\n")
|
18
|
+
|
19
|
+
options[:format] = :tsv
|
20
|
+
parser.on("-f", "--format FMT", "Write to format (TSV or Ruby)") do |fmt|
|
21
|
+
options[:format] = fmt.downcase.to_sym
|
22
|
+
end
|
23
|
+
|
24
|
+
parser.on("-h", "--help", "Display this usage information") do
|
25
|
+
puts parser
|
26
|
+
exit
|
27
|
+
end
|
28
|
+
end
|
29
|
+
optparse.parse!
|
30
|
+
unless ARGV.size == 2
|
31
|
+
puts optparse
|
32
|
+
exit(1)
|
33
|
+
end
|
34
|
+
options
|
35
|
+
end
|
36
|
+
|
37
|
+
options = parse_options
|
38
|
+
|
39
|
+
require "cacofonix"
|
40
|
+
extractor = Cacofonix::CodeListExtractor.new(ARGV.shift, options[:format])
|
41
|
+
extractor.run(ARGV.shift)
|