relaton-render 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.github/workflows/rake.yml +15 -0
- data/.hound.yml +5 -0
- data/.rubocop.yml +10 -0
- data/Gemfile +8 -0
- data/LICENSE.txt +25 -0
- data/README.adoc +241 -0
- data/Rakefile +6 -0
- data/bin/console +14 -0
- data/bin/rspec +18 -0
- data/bin/setup +8 -0
- data/lib/isodoc/i18n.rb +24 -0
- data/lib/isodoc-yaml/i18n-ar.yaml +2 -0
- data/lib/isodoc-yaml/i18n-de.yaml +2 -0
- data/lib/isodoc-yaml/i18n-en.yaml +22 -0
- data/lib/isodoc-yaml/i18n-es.yaml +2 -0
- data/lib/isodoc-yaml/i18n-fr.yaml +2 -0
- data/lib/isodoc-yaml/i18n-ru.yaml +23 -0
- data/lib/isodoc-yaml/i18n-zh-Hans.yaml +2 -0
- data/lib/parse/parse.rb +54 -0
- data/lib/parse/parse_contributors.rb +96 -0
- data/lib/parse/parse_extract.rb +155 -0
- data/lib/relaton/config.yml +67 -0
- data/lib/relaton/render.rb +123 -0
- data/lib/relaton/render_classes.rb +126 -0
- data/lib/relaton/render_fields.rb +151 -0
- data/lib/relaton/version.rb +5 -0
- data/lib/relaton-render.rb +6 -0
- data/lib/template/template.rb +152 -0
- data/lib/utils/utils.rb +27 -0
- data/relaton-render.gemspec +35 -0
- metadata +213 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA256:
|
3
|
+
metadata.gz: 900cfb8e591fbbd83ee48c2dfa762a317a15c590fb89844b3ce7a759125d4f94
|
4
|
+
data.tar.gz: 29c15ba8cfe1e2dcfafc8d6a4d9985ed298c4515d4c734e3505dfcca9cb11189
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: ebd7be4d34144997dcee8593266b75eefca1781341b4f081df290a9df64cbb7d665985c1bd0807c1036b190f68d6877b2bf822281bdc6e7c3a332fce349ac612
|
7
|
+
data.tar.gz: 8392d3b4d8c836b74cbf7a05435f55b274f24ae1004b247151481a34d86c104818926f3452c68f776a0adb521e9404b908f0d0fde25494014958bfd2c28005ac
|
@@ -0,0 +1,15 @@
|
|
1
|
+
# Auto-generated by Cimas: Do not edit it manually!
|
2
|
+
# See https://github.com/metanorma/cimas
|
3
|
+
name: rake
|
4
|
+
|
5
|
+
on:
|
6
|
+
push:
|
7
|
+
branches: [ master, main ]
|
8
|
+
tags: [ v* ]
|
9
|
+
pull_request:
|
10
|
+
|
11
|
+
jobs:
|
12
|
+
rake:
|
13
|
+
uses: metanorma/metanorma-build-scripts/.github/workflows/generic-rake.yml@main
|
14
|
+
secrets:
|
15
|
+
pat_token: ${{ secrets.METANORMA_CI_PAT_TOKEN }}
|
data/.hound.yml
ADDED
data/.rubocop.yml
ADDED
@@ -0,0 +1,10 @@
|
|
1
|
+
# Auto-generated by Cimas: Do not edit it manually!
|
2
|
+
# See https://github.com/metanorma/cimas
|
3
|
+
inherit_from:
|
4
|
+
- https://raw.githubusercontent.com/riboseinc/oss-guides/master/ci/rubocop.yml
|
5
|
+
|
6
|
+
# local repo-specific modifications
|
7
|
+
# ...
|
8
|
+
|
9
|
+
AllCops:
|
10
|
+
TargetRubyVersion: 2.5
|
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,25 @@
|
|
1
|
+
BSD 2-Clause License
|
2
|
+
|
3
|
+
Copyright (c) 2018, Ribose
|
4
|
+
All rights reserved.
|
5
|
+
|
6
|
+
Redistribution and use in source and binary forms, with or without
|
7
|
+
modification, are permitted provided that the following conditions are met:
|
8
|
+
|
9
|
+
* Redistributions of source code must retain the above copyright notice, this
|
10
|
+
list of conditions and the following disclaimer.
|
11
|
+
|
12
|
+
* Redistributions in binary form must reproduce the above copyright notice,
|
13
|
+
this list of conditions and the following disclaimer in the documentation
|
14
|
+
and/or other materials provided with the distribution.
|
15
|
+
|
16
|
+
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
|
17
|
+
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
18
|
+
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
|
19
|
+
DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
|
20
|
+
FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
|
21
|
+
DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
|
22
|
+
SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
|
23
|
+
CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
|
24
|
+
OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
25
|
+
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
data/README.adoc
ADDED
@@ -0,0 +1,241 @@
|
|
1
|
+
= Relaton Render
|
2
|
+
|
3
|
+
image:https://img.shields.io/gem/v/iso690render.svg["Gem Version", link="https://rubygems.org/gems/iso690render"]
|
4
|
+
image:https://github.com/metanorma/iso690render/workflows/rake/badge.svg["Build Status", link="https://github.com/metanorma/iso690render/actions?workflow=rake"]
|
5
|
+
image:https://codeclimate.com/github/metanorma/iso690render/badges/gpa.svg["Code Climate", link="https://codeclimate.com/github/metanorma/iso690render"]
|
6
|
+
|
7
|
+
Gem that takes a https://github.com/relaton/relaton[Relaton] bibliographic description and
|
8
|
+
a configuration, and generates a https://www.metanorma.org[Metanorma] XML rendering of that description.
|
9
|
+
|
10
|
+
== Calling
|
11
|
+
|
12
|
+
[source,ruby]
|
13
|
+
----
|
14
|
+
input = "<bibitem type='...'>....</bibitem>"
|
15
|
+
|
16
|
+
Relaton::Render::General.new(template: ..., nametemplate: ..., seriestemplate: ..., language: "en", script: "Latn").render(input)
|
17
|
+
----
|
18
|
+
|
19
|
+
The gem is intended to be inherited from by Metanorma flavours, which may specialise it with their own
|
20
|
+
code. The templates are however intended to determine much of the rendering.
|
21
|
+
|
22
|
+
Gems can provide their configurations in YAML files, and parse them before passing them to the call to Iso690Render.
|
23
|
+
The built-in values for Iso690Render are given in `/lib/iso690render/config.yml`, and can be overridden by
|
24
|
+
the parameters of initialising Iso690Render.
|
25
|
+
|
26
|
+
The parameters are:
|
27
|
+
|
28
|
+
`language`:: in ISO-639
|
29
|
+
`script`:: in ISO-15124
|
30
|
+
`template`:: templates for rendering different bibliographic types
|
31
|
+
`nametemplate`:: templates for rendering personal names
|
32
|
+
`seriestemplate`:: template for rendering series
|
33
|
+
`journaltemplate`:: template for rendering journals in article citations
|
34
|
+
`extenttemplate`:: templates for rendering extents
|
35
|
+
`edition_number`:: override formatting of edition number
|
36
|
+
`edition`:: override formatting of edition
|
37
|
+
`date`:: default date format (from Twitter CLDR)
|
38
|
+
|
39
|
+
== Configuration
|
40
|
+
|
41
|
+
=== Templates
|
42
|
+
|
43
|
+
There is one template provided for each of the bibliographic types recognised by Relaton (`/bibitem/@type`), and a default template:
|
44
|
+
|
45
|
+
Currently supported:
|
46
|
+
|
47
|
+
* article
|
48
|
+
* book
|
49
|
+
* booklet
|
50
|
+
* manual
|
51
|
+
* proceedings
|
52
|
+
* presentation
|
53
|
+
* thesis
|
54
|
+
* techreport
|
55
|
+
* standard
|
56
|
+
* unpublished
|
57
|
+
* electronic resource
|
58
|
+
* inbook
|
59
|
+
* incollection
|
60
|
+
* inproceedings
|
61
|
+
* journal
|
62
|
+
* website
|
63
|
+
* webresource
|
64
|
+
* dataset
|
65
|
+
|
66
|
+
Not currently supported:
|
67
|
+
|
68
|
+
* map
|
69
|
+
* audiovisual
|
70
|
+
* film
|
71
|
+
* video
|
72
|
+
* broadcast
|
73
|
+
* software
|
74
|
+
* graphic_work
|
75
|
+
* music
|
76
|
+
* performance
|
77
|
+
* patent
|
78
|
+
* archival
|
79
|
+
* social_media
|
80
|
+
* alert
|
81
|
+
* message
|
82
|
+
* conversation
|
83
|
+
* misc (default)
|
84
|
+
|
85
|
+
|
86
|
+
In Metanorma, not all types are used, but there are exemplars for all of these given on this site, following
|
87
|
+
the human-readable style used in ISO 690. These can be overridden by supplying corresponding paramerers in the call
|
88
|
+
to initialise Iso690Render.
|
89
|
+
|
90
|
+
Each `template` is a string marked up with https://shopify.github.io/liquid/[Liquid Markup], with the following fields
|
91
|
+
drawn from the bibliographic item:
|
92
|
+
|
93
|
+
|===
|
94
|
+
| Field | Relaton XPath | Multiple | Can come from host | Note
|
95
|
+
|
96
|
+
| title | ./title | | |
|
97
|
+
| edition | ./edition | | Y | If numeric value, is given internationalised rendering of "nth edition", as set in edition_numbering. Otherwise, the textual content of the tag is given.
|
98
|
+
| edition_raw | ./edition | | Y | The strict textual content of the tag is given.
|
99
|
+
| medium | ./medium | | Y |
|
100
|
+
| place | ./place | | Y |
|
101
|
+
| publisher | ./contributor[role/@type = 'publisher']/organization/name | | Y |
|
102
|
+
| distributor | ./contributor[role/@type = 'distributor']/organization/name | | Y |
|
103
|
+
| standardidentifier | ./docidentifier[not(@type = 'metanorma' or @type = 'ordinal')] | Y | |
|
104
|
+
| status | ./status | | | Rendering varies by flavour
|
105
|
+
| uri | ./uri[@type = 'doi' or @type = 'uri' or @type = 'src' or true] | | |
|
106
|
+
| access_location | ./accessLocation | | Y |
|
107
|
+
| extent | ./extent | Y | | Render with standard abbreviations for pp, vols, with n-dash, with delimiting of multiple locations
|
108
|
+
| creatornames | ./contributor[role/@type = 'author'] \| ./contributor[role/@type = 'performer'] \| ./contributor[role/@type = 'adapter'] \| ./contributor[role/@type = 'translator'] \| ./contributor[role/@type = 'editor'] \| ./contributor[role/@type = 'publisher'] \| ./contributor[role/@type = 'distributor'] \| ./contributor | Y | | <<nametemplate,`nametemplate`>> applied to each name; joining template from internationalisation applied to multiple names
|
109
|
+
| role | ./contributor[role/description] \| ./contributor[role/@type] | | |
|
110
|
+
| date | ./date[@type = 'issued'] \| ./date[@type = 'circulated'] \| ./date | | Y |
|
111
|
+
| date_updated | ./date[@type = 'updated'] | | Y |
|
112
|
+
| date_accessed | ./date[@type = 'accessed'] | | Y |
|
113
|
+
| series | ./series[@type = 'main' or not(@type) or true] | | Y | <<seriestemplate,`seriestemplate`>> applies to series
|
114
|
+
| host_creatornames | ./relation[@type = 'includedIn']/ bibitem/contributor[role/@type = 'author'] | | Y | Follows options for `creatornames`
|
115
|
+
| host_title | ./relation[@type = 'includedIn']/ bibitem/title | Y | Y | Follows options for `creatornames`
|
116
|
+
| host_role | ./relation[@type = 'includedIn']/ bibitem/contributor[role/description] \| ./relation[@type = 'includedIn']/ bibitem/contributor[role/@type] | | Y |
|
117
|
+
| type | ./@type | |
|
118
|
+
| labels | | | text to be looked up in internationalisation configuration files: "edition", "In", "At", "Vol", "Vols", "p.", "pp"
|
119
|
+
|===
|
120
|
+
|
121
|
+
Many fields are populated either by the description of the bibliographic item itself, or by the description of the item containing it (the _host_ item: `./relation[@type = 'includedIn']/bibitem`). For example, in a paper included in an edited volume, the edition will typically be given for the editor volume, rather than for the paper. Those fields are indicated by "Can come from host" in the table.
|
122
|
+
|
123
|
+
The Liquid template surrounds each field by preceding and following punctuation.
|
124
|
+
|
125
|
+
* Fields are space-delimited. So `<em>{{ title }}</em> [{{medium}}]` are two separate fields.
|
126
|
+
* If fields are not space-delimited, this is indicated by inserting `|`. So `{{ title }}|{{ medium}}` is two fields, rendered with no space separation.
|
127
|
+
* If the field is empty, its surrounding markup is also removed. So if there is no medium, then `[{{medium}}]` is not rendered, and the brackets will be stripped.
|
128
|
+
* Underscore is treated as space, attaching to the preceding or following field. So `,_{{ edition }}_{{ labels['edition'] }}` is treated as the one field.
|
129
|
+
* If punctuation is space delimited, it is inserted regardless of preceding content. So `{{ creatornames }} ({{date}}) .` will insert the full stop whether or not the date is present.
|
130
|
+
* Space between punctuation and before punctuation is automatically removed.
|
131
|
+
|
132
|
+
For example:
|
133
|
+
|
134
|
+
....
|
135
|
+
"{{ creatornames }} ({{date}}) . <em>{{ title }}</em> [{{medium}}] ,_{{ edition }}_{{ labels['edition'] }} ."
|
136
|
+
....
|
137
|
+
|
138
|
+
If a type uses another type's template, the type is mapped to the other type's name; e.g.
|
139
|
+
|
140
|
+
....
|
141
|
+
template:
|
142
|
+
book: ...
|
143
|
+
booklet: book
|
144
|
+
....
|
145
|
+
|
146
|
+
[[nametemplate]]
|
147
|
+
=== Name templates
|
148
|
+
|
149
|
+
The `nametemplate` is a hash of Liquid templates for the formatting of contributor names in particular positions. It
|
150
|
+
draws on the following fields drawn from the bibliographic item:
|
151
|
+
|
152
|
+
|===
|
153
|
+
| Field | Relaton XPath | Multiple | Note
|
154
|
+
|
155
|
+
| surname[0] | ./contributor[1]/person/name/surname \| ./contributor[1]/person/name/completename \| ./contributor[1]/organization/name | | i.e. surname is the name default
|
156
|
+
| surname[1] | ./contributor[2]/name/surname | |
|
157
|
+
| surname[2] | ./contributor[3]/name/surname | |
|
158
|
+
| initials[0] | ./contributor[1]/name/initial | | If not supplied, the first letter of each given name is used instead
|
159
|
+
| initials[1] | ./contributor[2]/name/initial | |
|
160
|
+
| given[0] | ./contributor[1]/name/forename[1] | | If not supplied, initials are used instead
|
161
|
+
| given[1] | ./contributor[2]/name/forename[1] | |
|
162
|
+
| middle[0] | ./contributor[1]/name/forename[not(first())] | Y |
|
163
|
+
| middle[1] | ./contributor[2]/name/forename[not(first())] | Y |
|
164
|
+
|===
|
165
|
+
|
166
|
+
There are at least three distinct `nametemplate` instances that need to be provided, one for a single contributor (`one:`), one for two contributors (`two:`), one for three or more (`more:`), and optionally one for "et al." (`etal:`). The number of contributors for which "et al." starts being used is indicated by `etal_count`.
|
167
|
+
|
168
|
+
For example:
|
169
|
+
....
|
170
|
+
{
|
171
|
+
one: "{{ surname[0] }}, {{ given[0] }} {{ middle[0] | slice : 0 }}",
|
172
|
+
two: "{{ surname[0] }}, {{ given[0] }} {{ middle[0] | slice : 0 }} & {{ given[1] }} {{ middle[1] | slice : 0 }} {{ surname[1] }}",
|
173
|
+
more: "{{ surname[0] }}, {{ given[0] }} {{ middle[0] | slice : 0 }}, {{ given[1] }} {{ middle[1] | slice : 0 }} {{ surname[1] }} & {{ given[2] }} {{ middle[2] | slice : 0 }} {{ surname[2] }}",
|
174
|
+
etal: "{{ surname[0] }}, {{ given[0] }} {{ middle[0] | slice : 0 }}, {{ given[1] }} {{ middle[1] | slice : 0 }} {{ surname[1] }} <em>et al.</em>",
|
175
|
+
etal_count: 6
|
176
|
+
}
|
177
|
+
....
|
178
|
+
|
179
|
+
In the case of `more`, the `(name)[1]` entries are repeated for all additional authors above 2 and before the final author.
|
180
|
+
|
181
|
+
[[seriestemplate]]
|
182
|
+
=== Series template
|
183
|
+
|
184
|
+
The `seriestemplate` is a template for the rendering of series information. It draws on the following fields drawn from the bibliographic item:
|
185
|
+
|
186
|
+
|===
|
187
|
+
| Field | Relaton XPath | Multiple | Can come from host | Note
|
188
|
+
|
189
|
+
| series_title | ./series[@type = 'main' or not(@type) or true]/name | | Y |
|
190
|
+
| series_abbr | ./series[@type = 'main' or not(@type) or true]/abbreviation | | Y |
|
191
|
+
| series_num | ./series[@type = 'main' or not(@type) or true]/number | | Y |
|
192
|
+
| series_partnumber | ./series[@type = 'main' or not(@type) or true]/partnumber | | Y |
|
193
|
+
| series_run | ./series[@type = 'main' or not(@type) or true]/run | | Y |
|
194
|
+
|===
|
195
|
+
|
196
|
+
For example: `{% if series_abbr %}{{series_abbr}}{% else %}{{series_title}}{% endif %} ,_({{series_run}}) {{series_num}}|({{series_partnumber}})`
|
197
|
+
|
198
|
+
=== Journal template
|
199
|
+
|
200
|
+
The `journaltemplate` is a template for the rendering of series information, when they relate to articles in a journal. The template is distinct because of longstanding practice of rendering journal information differently from monograph series information. The template draws on the same fields as the `seriestemplate`, but because the journal title is typically italicised and the numeration is not, any italicisation needs to occur within the template.
|
201
|
+
|
202
|
+
For example, the recommended practice in the current edition of ISO 690 is to give explicit volume labels:
|
203
|
+
|
204
|
+
`<em>{% if series_abbr %}{{series_abbr}}{% else %}{{series_title}}{% endif %}</em> {{ labels['volume'] }}_{{series_num}} {{ labels['part'] }}_{{series_partnumber}}`
|
205
|
+
|
206
|
+
A common template that drops those labels is:
|
207
|
+
|
208
|
+
`<em>{% if series_abbr %}{{series_abbr}}{% else %}{{series_title}}{% endif %}</em> {{series_num}}|({{series_partnumber}})`
|
209
|
+
|
210
|
+
=== Extent template
|
211
|
+
|
212
|
+
The extent of a reference can be expressed differently depending on the type of bibliographic item. For example, the extent of a book is its page count, and is typically expressed as something like _59 pp._ On the other hand, the extent of an article is expressed as _pp. 9–20_, or just _9–20_.
|
213
|
+
|
214
|
+
To capture this, a separate template is supplied under `extenttemplate` for each bibliographic item type. For those types where none is supplied, the template given for `misc` is used as the default.
|
215
|
+
|
216
|
+
The template draws on the defined types of locality of extents; the most common of these is `page` and `volume`. Locality types are the fields used in the Liquid templates; for example:
|
217
|
+
|
218
|
+
....
|
219
|
+
{
|
220
|
+
book: "{{ volume }}_{{ label['extent']['volume'] }}, {{ page }}_{{ label['extent']['page'] }}"
|
221
|
+
inbook: "{{ volume }}: {{ page }}"
|
222
|
+
misc: "{{ label['extent']['volume'] }}_{{ volume }}, {{ label['extent']['page'] }}_{{ page }}"
|
223
|
+
}
|
224
|
+
....
|
225
|
+
|
226
|
+
The internationalisation files define a singular and a plural version of the locality types, under `labels['extent']`
|
227
|
+
|
228
|
+
* The plural is always used if the extent is a range (with a `<from>` and `<to>`).
|
229
|
+
* In a host type of bibliographic item, the extent is singular only if the value is `1`, else it is plural (_1 p._, _2 pp._)
|
230
|
+
* In an included item (`inbook`, `incollection`, `inproceedings`, `article`, or any item with an `includedIn` relation),
|
231
|
+
the singular is used if the extent is not a range (_pp. 2–4_ vs. _p. 3_)..
|
232
|
+
|
233
|
+
=== Other
|
234
|
+
|
235
|
+
In addition, the configuration includes different configuration options for rendering:
|
236
|
+
|
237
|
+
The internationalisation file sets the following variables, which can be overridden in configuration parameters:
|
238
|
+
`edition_number`:: has following values corresponding to the rule-based number rules defined in https://github.com/twitter/twitter-cldr-rb[Twitter CLDR]
|
239
|
+
for a language. For example, English _4th_ is defined as `["OrdinalRules", "digits-ordinal"]`, because under twitter-cldr, `4th` is generated as `4.localize(:en).to_rbnf_s("OrdinalRules", "digits-ordinal")`.
|
240
|
+
`edition`:: is the localised expression for edition, with the edition number given as %. So _4th ed.` is generated with `edition` as `% ed.`.
|
241
|
+
`date`:: date format default, taken from https://github.com/twitter/twitter-cldr-rb[Twitter CLDR]: `to_full_s`, `to_long_s`, `to_medium_s`, `to_short_s`, or one of the `to_additional_s` formats. One value is given for each of "month_year", "day_month_year", and "date_time"; e.g. `{ month_year: to_long_s, day_month_year: to_long_s, date_time: to_long_s }`.
|
data/Rakefile
ADDED
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "cnccs"
|
5
|
+
|
6
|
+
# You can add fixtures and/or initialization code here to make experimenting
|
7
|
+
# with your gem easier. You can also use a different console, if you like.
|
8
|
+
|
9
|
+
# (If you use this, don't forget to add pry to your Gemfile!)
|
10
|
+
# require "pry"
|
11
|
+
# Pry.start
|
12
|
+
|
13
|
+
require "irb"
|
14
|
+
IRB.start(__FILE__)
|
data/bin/rspec
ADDED
@@ -0,0 +1,18 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
# This file was generated by Bundler.
|
4
|
+
#
|
5
|
+
# The application 'rspec' is installed as part of a gem, and
|
6
|
+
# this file is here to facilitate running it.
|
7
|
+
#
|
8
|
+
|
9
|
+
require "pathname"
|
10
|
+
ENV["BUNDLE_GEMFILE"] ||= File.expand_path(
|
11
|
+
"../../Gemfile", Pathname.new(__FILE__).realpath
|
12
|
+
)
|
13
|
+
|
14
|
+
require "rubygems"
|
15
|
+
require "bundler/setup"
|
16
|
+
|
17
|
+
load Gem.bin_path("rspec-core", "rspec")
|
18
|
+
|
data/bin/setup
ADDED
data/lib/isodoc/i18n.rb
ADDED
@@ -0,0 +1,24 @@
|
|
1
|
+
require "yaml"
|
2
|
+
require "isodoc-i18n"
|
3
|
+
|
4
|
+
module IsoDoc
|
5
|
+
class I18n
|
6
|
+
def load_yaml1(lang, script)
|
7
|
+
case lang
|
8
|
+
when "en", "fr", "ru", "de", "es", "ar"
|
9
|
+
load_yaml2(lang)
|
10
|
+
when "zh"
|
11
|
+
if script == "Hans" then load_yaml2("zh-Hans")
|
12
|
+
else load_yaml2("en")
|
13
|
+
end
|
14
|
+
else
|
15
|
+
load_yaml2("en")
|
16
|
+
end
|
17
|
+
end
|
18
|
+
|
19
|
+
def load_yaml2(str)
|
20
|
+
YAML.load_file(File.join(File.dirname(__FILE__),
|
21
|
+
"../isodoc-yaml/i18n-#{str}.yaml"))
|
22
|
+
end
|
23
|
+
end
|
24
|
+
end
|
@@ -0,0 +1,22 @@
|
|
1
|
+
in: in
|
2
|
+
at: at
|
3
|
+
and: and
|
4
|
+
updated: updated
|
5
|
+
viewed: viewed
|
6
|
+
version: version
|
7
|
+
date:
|
8
|
+
month_year: to_long_s
|
9
|
+
day_month_year: to_long_s
|
10
|
+
date_time: to_long_s
|
11
|
+
edition_number: ["OrdinalRules", "digits-ordinal"]
|
12
|
+
edition: "% edition"
|
13
|
+
editor:
|
14
|
+
sg: ed.
|
15
|
+
pl: eds.
|
16
|
+
extent:
|
17
|
+
page:
|
18
|
+
sg: p.
|
19
|
+
pl: pp.
|
20
|
+
volume:
|
21
|
+
sg: vol.
|
22
|
+
pl: vols.
|
@@ -0,0 +1,23 @@
|
|
1
|
+
in: в
|
2
|
+
at: в
|
3
|
+
and: и
|
4
|
+
updated: обновлен
|
5
|
+
viewed: просмотрено
|
6
|
+
version: версия
|
7
|
+
date:
|
8
|
+
month_year: to_long_s
|
9
|
+
day_month_year: to_long_s
|
10
|
+
date_time: to_long_s
|
11
|
+
edition_number: ["SpelloutRules", "spellout-ordinal-neuter"]
|
12
|
+
edition: "% издание"
|
13
|
+
editor:
|
14
|
+
sg: изд.
|
15
|
+
pl: изд.
|
16
|
+
extent:
|
17
|
+
page:
|
18
|
+
sg: стр.
|
19
|
+
pl: стр.
|
20
|
+
volume:
|
21
|
+
sg: т.
|
22
|
+
pl: тт.
|
23
|
+
|
data/lib/parse/parse.rb
ADDED
@@ -0,0 +1,54 @@
|
|
1
|
+
require "nokogiri"
|
2
|
+
require "twitter_cldr"
|
3
|
+
require_relative "parse_contributors"
|
4
|
+
require_relative "parse_extract"
|
5
|
+
|
6
|
+
class Iso690Parse
|
7
|
+
def initialize; end
|
8
|
+
|
9
|
+
def extract(doc)
|
10
|
+
host = doc.at("./relation[@type = 'includedIn']/bibitem")
|
11
|
+
simple_xml2hash(doc).merge(simple_or_host_xml2hash(doc, host))
|
12
|
+
.merge(host_xml2hash(host))
|
13
|
+
.merge(series_xml2hash(doc, host))
|
14
|
+
end
|
15
|
+
|
16
|
+
def simple_xml2hash(doc)
|
17
|
+
creators, role = creatornames(doc)
|
18
|
+
{ type: type(doc), title: title(doc), extent_raw: extent(doc),
|
19
|
+
standardidentifier: standardidentifier(doc), uri: uri(doc),
|
20
|
+
status: status(doc), creators: creators, role_raw: role }
|
21
|
+
end
|
22
|
+
|
23
|
+
def simple_or_host_xml2hash(doc, host)
|
24
|
+
{ edition_raw: edition(doc, host), medium: medium(doc, host),
|
25
|
+
place: place(doc, host), publisher: publisher(doc, host),
|
26
|
+
distributor: distributor(doc, host),
|
27
|
+
access_location: access_location(doc, host),
|
28
|
+
date: date(doc, host), date_updated: date_updated(doc, host),
|
29
|
+
date_accessed: date_accessed(doc, host) }
|
30
|
+
end
|
31
|
+
|
32
|
+
def host_xml2hash(host)
|
33
|
+
creators, role = creatornames(host)
|
34
|
+
{ host_creators: creators, host_role_raw: role, host_title: title(host) }
|
35
|
+
end
|
36
|
+
|
37
|
+
def series_xml2hash(doc, host)
|
38
|
+
series = doc.at("./series[@type = 'main']") ||
|
39
|
+
doc.at("./series[not(@type)]") || doc.at("./series")
|
40
|
+
host and series ||=
|
41
|
+
host.at("./series[@type = 'main']") ||
|
42
|
+
host.at("./series[not(@type)]") || host.at("./series")
|
43
|
+
|
44
|
+
series_xml2hash1(series)
|
45
|
+
end
|
46
|
+
|
47
|
+
def series_xml2hash1(series)
|
48
|
+
return {} unless series
|
49
|
+
|
50
|
+
{ series_title: series_title(series), series_abbr: series_abbr(series),
|
51
|
+
series_run: series_run(series), series_num: series_num(series),
|
52
|
+
series_partnumber: series_partnumber(series) }
|
53
|
+
end
|
54
|
+
end
|
@@ -0,0 +1,96 @@
|
|
1
|
+
class Iso690Parse
|
2
|
+
def extract_orgname(org)
|
3
|
+
name = org.at("./name")
|
4
|
+
name&.text
|
5
|
+
end
|
6
|
+
|
7
|
+
def extract_personname(person)
|
8
|
+
surname = person.at("./name/surname") || person.at("./name/completename")
|
9
|
+
given, middle, initials = given_and_middle_name(person)
|
10
|
+
{ surname: surname&.text,
|
11
|
+
given: given,
|
12
|
+
middle: middle,
|
13
|
+
initials: initials }
|
14
|
+
end
|
15
|
+
|
16
|
+
def given_and_middle_name(person)
|
17
|
+
forenames = person.xpath("./name/forename")&.map(&:text)
|
18
|
+
initials = person.xpath("./name/initial")&.map(&:text)
|
19
|
+
forenames.empty? and initials.empty? and return [nil, nil, nil]
|
20
|
+
forenames.empty? and forenames = initials.dup
|
21
|
+
initials.empty? and initials = forenames.map { |x| x[0] }
|
22
|
+
[forenames.first, forenames[1..-1], initials]
|
23
|
+
end
|
24
|
+
|
25
|
+
def extractname(contributor)
|
26
|
+
org = contributor.at("./organization")
|
27
|
+
person = contributor.at("./person")
|
28
|
+
return { surname: extract_orgname(org) } if org
|
29
|
+
return extract_personname(person) if person
|
30
|
+
|
31
|
+
nil
|
32
|
+
end
|
33
|
+
|
34
|
+
def contributor_role(contributors)
|
35
|
+
return nil unless contributors.length.positive?
|
36
|
+
|
37
|
+
desc = contributors[0].at("role/description")&.text
|
38
|
+
type = contributors[0].at("role/@type")&.text
|
39
|
+
return nil if %w(author publisher).include?(type) && desc.nil?
|
40
|
+
|
41
|
+
type
|
42
|
+
end
|
43
|
+
|
44
|
+
def creatornames(doc)
|
45
|
+
cr = creatornames1(doc)
|
46
|
+
cr.empty? and return [nil, nil]
|
47
|
+
[cr.map { |x| extractname(x) }, contributor_role(cr)]
|
48
|
+
end
|
49
|
+
|
50
|
+
def creatornames1(doc)
|
51
|
+
cr = []
|
52
|
+
return cr if doc.nil?
|
53
|
+
|
54
|
+
%w(author performer adapter translator editor publisher distributor)
|
55
|
+
.each do |r|
|
56
|
+
add = doc.xpath("./contributor[role/@type = '#{r}']")
|
57
|
+
next if add.empty?
|
58
|
+
|
59
|
+
cr = add and break
|
60
|
+
end
|
61
|
+
cr.empty? and cr = doc.xpath("./contributor")
|
62
|
+
cr
|
63
|
+
end
|
64
|
+
|
65
|
+
def date1(date)
|
66
|
+
on = date.at("./on")
|
67
|
+
from = date.at("./from")
|
68
|
+
to = date.at("./to")
|
69
|
+
return { on: on.text } if on
|
70
|
+
return { from: from.text, to: to&.text } if from
|
71
|
+
|
72
|
+
nil
|
73
|
+
end
|
74
|
+
|
75
|
+
def date(doc, host)
|
76
|
+
x = doc.at("./date[@type = 'issued']") ||
|
77
|
+
doc.at("./date[@type = 'circulated']") ||
|
78
|
+
doc.at("./date") ||
|
79
|
+
host&.at("./date[@type = 'issued']") ||
|
80
|
+
host&.at("./date[@type = 'circulated']") ||
|
81
|
+
host&.at("./date") or return nil
|
82
|
+
date1(x)
|
83
|
+
end
|
84
|
+
|
85
|
+
def date_updated(doc, host)
|
86
|
+
x = doc.at("./date[@type = 'updated']") ||
|
87
|
+
host&.at("./date[@type = 'updated']") or return nil
|
88
|
+
date1(x)
|
89
|
+
end
|
90
|
+
|
91
|
+
def date_accessed(doc, host)
|
92
|
+
x = doc.at("./date[@type = 'accessed']") ||
|
93
|
+
host&.at("./date[@type = 'accessed']") or return nil
|
94
|
+
date1(x)
|
95
|
+
end
|
96
|
+
end
|