metanorma-standoc 2.2.5 → 2.2.6
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.github/workflows/automerge.yml +31 -0
- data/lib/isodoc/html/htmlstyle.css +1 -1
- data/lib/metanorma/standoc/base.rb +1 -0
- data/lib/metanorma/standoc/basicdoc.rng +0 -27
- data/lib/metanorma/standoc/biblio-standoc.rng +164 -0
- data/lib/metanorma/standoc/biblio.rng +45 -18
- data/lib/metanorma/standoc/cleanup.rb +1 -0
- data/lib/metanorma/standoc/cleanup_asciibib.rb +110 -0
- data/lib/metanorma/standoc/cleanup_biblio.rb +5 -111
- data/lib/metanorma/standoc/cleanup_block.rb +7 -6
- data/lib/metanorma/standoc/cleanup_boilerplate.rb +6 -6
- data/lib/metanorma/standoc/cleanup_inline.rb +2 -2
- data/lib/metanorma/standoc/cleanup_text.rb +10 -3
- data/lib/metanorma/standoc/inline.rb +3 -1
- data/lib/metanorma/standoc/isodoc-compile.rng +7 -0
- data/lib/metanorma/standoc/isodoc.rng +23 -195
- data/lib/metanorma/standoc/validate.rb +8 -8
- data/lib/metanorma/standoc/version.rb +1 -1
- data/metanorma-standoc.gemspec +0 -1
- data/spec/metanorma/biblio_spec.rb +152 -144
- data/spec/metanorma/cleanup_sections_spec.rb +1 -2
- data/spec/metanorma/cleanup_spec.rb +11 -0
- data/spec/metanorma/inline_spec.rb +63 -2
- data/spec/metanorma/macros_plantuml_spec.rb +4 -4
- data/spec/support/shared_examples/structured_data_2_text_preprocessor.rb +3 -3
- data/spec/vcr_cassettes/bsi16341.yml +70 -72
- data/spec/vcr_cassettes/dated_iso_ref_joint_iso_iec.yml +82 -82
- data/spec/vcr_cassettes/dated_iso_ref_joint_iso_iec1.yml +12 -12
- data/spec/vcr_cassettes/hide_refs.yml +58 -58
- data/spec/vcr_cassettes/isobib_get_123.yml +13 -13
- data/spec/vcr_cassettes/isobib_get_123_1.yml +22 -22
- data/spec/vcr_cassettes/isobib_get_123_1_fr.yml +33 -33
- data/spec/vcr_cassettes/isobib_get_123_2.yml +25 -25
- data/spec/vcr_cassettes/isobib_get_123_2001.yml +12 -12
- data/spec/vcr_cassettes/isobib_get_124.yml +12 -12
- data/spec/vcr_cassettes/rfcbib_get_rfc8341.yml +37 -21
- data/spec/vcr_cassettes/separates_iev_citations_by_top_level_clause.yml +45 -45
- data/spec/vcr_cassettes/std-link.yml +12 -12
- metadata +6 -16
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: '033585c8aaadb0c5672e328edd9c30012ee330cb800cbf8a7f4e2a7e5498a61e'
|
|
4
|
+
data.tar.gz: 07b1cba33ba7917f68429d91393c8795d787c63e06f60d3f8d00938088e13138
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: d163281f43172f6c1be2391bb923245f58270efd2f1eb482412b08e41ebdfeed91f6edeb4df61e4e5056feba0fd7c17b673b8d8d324f9837f93ac310052eda73
|
|
7
|
+
data.tar.gz: 1a8dbeadcc05872bf5daadebf262204461e75f9e39ffd9a0d2b77ebaec68131cd04786cb22a8adfaccfdaf3cad3db3019a51a85b18d8be1a8d363381c7618045
|
|
@@ -0,0 +1,31 @@
|
|
|
1
|
+
# Auto-generated by Cimas: Do not edit it manually!
|
|
2
|
+
# See https://github.com/metanorma/cimas
|
|
3
|
+
# source: https://github.com/marketplace/actions/merge-pull-requests#usage
|
|
4
|
+
name: automerge
|
|
5
|
+
on:
|
|
6
|
+
pull_request:
|
|
7
|
+
types:
|
|
8
|
+
- labeled
|
|
9
|
+
- unlabeled
|
|
10
|
+
- synchronize
|
|
11
|
+
- opened
|
|
12
|
+
- edited
|
|
13
|
+
- ready_for_review
|
|
14
|
+
- reopened
|
|
15
|
+
- unlocked
|
|
16
|
+
pull_request_review:
|
|
17
|
+
types:
|
|
18
|
+
- submitted
|
|
19
|
+
check_suite:
|
|
20
|
+
types:
|
|
21
|
+
- completed
|
|
22
|
+
status: {}
|
|
23
|
+
jobs:
|
|
24
|
+
automerge:
|
|
25
|
+
runs-on: ubuntu-latest
|
|
26
|
+
steps:
|
|
27
|
+
- id: automerge
|
|
28
|
+
name: automerge
|
|
29
|
+
uses: "pascalgn/automerge-action@v0.15.3"
|
|
30
|
+
env:
|
|
31
|
+
GITHUB_TOKEN: "${{ secrets.GITHUB_TOKEN }}"
|
|
@@ -1,10 +1,5 @@
|
|
|
1
1
|
<?xml version="1.0" encoding="UTF-8"?>
|
|
2
2
|
<grammar xmlns="http://relaxng.org/ns/structure/1.0" datatypeLibrary="http://www.w3.org/2001/XMLSchema-datatypes">
|
|
3
|
-
<include href="biblio.rng">
|
|
4
|
-
<start>
|
|
5
|
-
<ref name="document"/>
|
|
6
|
-
</start>
|
|
7
|
-
</include>
|
|
8
3
|
<define name="document">
|
|
9
4
|
<element name="document">
|
|
10
5
|
<optional>
|
|
@@ -1125,26 +1120,4 @@
|
|
|
1125
1120
|
</zeroOrMore>
|
|
1126
1121
|
</element>
|
|
1127
1122
|
</define>
|
|
1128
|
-
<define name="ext">
|
|
1129
|
-
<element name="ext">
|
|
1130
|
-
<ref name="BibDataExtensionType"/>
|
|
1131
|
-
</element>
|
|
1132
|
-
</define>
|
|
1133
|
-
<define name="BibDataExtensionType">
|
|
1134
|
-
<ref name="doctype"/>
|
|
1135
|
-
</define>
|
|
1136
|
-
<define name="doctype">
|
|
1137
|
-
<element name="doctype">
|
|
1138
|
-
<ref name="DocumentType"/>
|
|
1139
|
-
</element>
|
|
1140
|
-
</define>
|
|
1141
|
-
<define name="DocumentType">
|
|
1142
|
-
<value>document</value>
|
|
1143
|
-
</define>
|
|
1144
|
-
<define name="BibData">
|
|
1145
|
-
<ref name="BibliographicItem"/>
|
|
1146
|
-
<optional>
|
|
1147
|
-
<ref name="ext"/>
|
|
1148
|
-
</optional>
|
|
1149
|
-
</define>
|
|
1150
1123
|
</grammar>
|
|
@@ -0,0 +1,164 @@
|
|
|
1
|
+
<?xml version="1.0" encoding="UTF-8"?>
|
|
2
|
+
<grammar xmlns="http://relaxng.org/ns/structure/1.0">
|
|
3
|
+
<!--
|
|
4
|
+
Add-ons to biblio.rnc for standoc model: defines the extension point BibDataExtensionType
|
|
5
|
+
of relaton
|
|
6
|
+
|
|
7
|
+
Specialisations as for biblio.rnc. Extension point can be redefined completely for a flavour of standoc
|
|
8
|
+
(SDO); but other elements in Bibdata can only be extended (more specialised vocabularies for Bibdata)
|
|
9
|
+
-->
|
|
10
|
+
<include href="biblio.rng">
|
|
11
|
+
<define name="BibData">
|
|
12
|
+
<ref name="BibliographicItem"/>
|
|
13
|
+
<optional>
|
|
14
|
+
<ref name="ext"/>
|
|
15
|
+
</optional>
|
|
16
|
+
</define>
|
|
17
|
+
</include>
|
|
18
|
+
<define name="ext">
|
|
19
|
+
<element name="ext">
|
|
20
|
+
<ref name="BibDataExtensionType"/>
|
|
21
|
+
</element>
|
|
22
|
+
</define>
|
|
23
|
+
<define name="BibDataExtensionType">
|
|
24
|
+
<optional>
|
|
25
|
+
<attribute name="schema-version"/>
|
|
26
|
+
</optional>
|
|
27
|
+
<ref name="doctype"/>
|
|
28
|
+
<optional>
|
|
29
|
+
<ref name="docsubtype"/>
|
|
30
|
+
</optional>
|
|
31
|
+
<optional>
|
|
32
|
+
<ref name="editorialgroup"/>
|
|
33
|
+
</optional>
|
|
34
|
+
<zeroOrMore>
|
|
35
|
+
<ref name="ics"/>
|
|
36
|
+
</zeroOrMore>
|
|
37
|
+
<zeroOrMore>
|
|
38
|
+
<ref name="structuredidentifier"/>
|
|
39
|
+
</zeroOrMore>
|
|
40
|
+
</define>
|
|
41
|
+
<define name="doctype">
|
|
42
|
+
<element name="doctype">
|
|
43
|
+
<optional>
|
|
44
|
+
<attribute name="abbreviation"/>
|
|
45
|
+
</optional>
|
|
46
|
+
<ref name="DocumentType"/>
|
|
47
|
+
</element>
|
|
48
|
+
</define>
|
|
49
|
+
<define name="DocumentType">
|
|
50
|
+
<value>document</value>
|
|
51
|
+
</define>
|
|
52
|
+
<define name="docsubtype">
|
|
53
|
+
<element name="subdoctype">
|
|
54
|
+
<ref name="DocumentSubtype"/>
|
|
55
|
+
</element>
|
|
56
|
+
</define>
|
|
57
|
+
<define name="DocumentSubtype">
|
|
58
|
+
<text/>
|
|
59
|
+
</define>
|
|
60
|
+
<define name="editorialgroup">
|
|
61
|
+
<element name="editorialgroup">
|
|
62
|
+
<oneOrMore>
|
|
63
|
+
<ref name="technical-committee"/>
|
|
64
|
+
</oneOrMore>
|
|
65
|
+
</element>
|
|
66
|
+
</define>
|
|
67
|
+
<define name="technical-committee">
|
|
68
|
+
<element name="technical-committee">
|
|
69
|
+
<ref name="IsoWorkgroup"/>
|
|
70
|
+
</element>
|
|
71
|
+
</define>
|
|
72
|
+
<define name="IsoWorkgroup">
|
|
73
|
+
<optional>
|
|
74
|
+
<attribute name="number"/>
|
|
75
|
+
</optional>
|
|
76
|
+
<optional>
|
|
77
|
+
<attribute name="type"/>
|
|
78
|
+
</optional>
|
|
79
|
+
<optional>
|
|
80
|
+
<attribute name="identifier"/>
|
|
81
|
+
</optional>
|
|
82
|
+
<optional>
|
|
83
|
+
<attribute name="prefix"/>
|
|
84
|
+
</optional>
|
|
85
|
+
<text/>
|
|
86
|
+
</define>
|
|
87
|
+
<define name="ics">
|
|
88
|
+
<element name="ics">
|
|
89
|
+
<element name="code">
|
|
90
|
+
<text/>
|
|
91
|
+
</element>
|
|
92
|
+
<optional>
|
|
93
|
+
<element name="text">
|
|
94
|
+
<text/>
|
|
95
|
+
</element>
|
|
96
|
+
</optional>
|
|
97
|
+
</element>
|
|
98
|
+
</define>
|
|
99
|
+
<define name="structuredidentifier">
|
|
100
|
+
<element name="structuredidentifier">
|
|
101
|
+
<optional>
|
|
102
|
+
<attribute name="type"/>
|
|
103
|
+
</optional>
|
|
104
|
+
<oneOrMore>
|
|
105
|
+
<element name="agency">
|
|
106
|
+
<text/>
|
|
107
|
+
</element>
|
|
108
|
+
</oneOrMore>
|
|
109
|
+
<optional>
|
|
110
|
+
<element name="class">
|
|
111
|
+
<text/>
|
|
112
|
+
</element>
|
|
113
|
+
</optional>
|
|
114
|
+
<element name="docnumber">
|
|
115
|
+
<text/>
|
|
116
|
+
</element>
|
|
117
|
+
<optional>
|
|
118
|
+
<element name="partnumber">
|
|
119
|
+
<text/>
|
|
120
|
+
</element>
|
|
121
|
+
</optional>
|
|
122
|
+
<optional>
|
|
123
|
+
<element name="edition">
|
|
124
|
+
<text/>
|
|
125
|
+
</element>
|
|
126
|
+
</optional>
|
|
127
|
+
<optional>
|
|
128
|
+
<element name="version">
|
|
129
|
+
<text/>
|
|
130
|
+
</element>
|
|
131
|
+
</optional>
|
|
132
|
+
<optional>
|
|
133
|
+
<element name="supplementtype">
|
|
134
|
+
<text/>
|
|
135
|
+
</element>
|
|
136
|
+
</optional>
|
|
137
|
+
<optional>
|
|
138
|
+
<element name="supplementnumber">
|
|
139
|
+
<text/>
|
|
140
|
+
</element>
|
|
141
|
+
</optional>
|
|
142
|
+
<optional>
|
|
143
|
+
<element name="amendment">
|
|
144
|
+
<text/>
|
|
145
|
+
</element>
|
|
146
|
+
</optional>
|
|
147
|
+
<optional>
|
|
148
|
+
<element name="corrigendum">
|
|
149
|
+
<text/>
|
|
150
|
+
</element>
|
|
151
|
+
</optional>
|
|
152
|
+
<optional>
|
|
153
|
+
<element name="language">
|
|
154
|
+
<text/>
|
|
155
|
+
</element>
|
|
156
|
+
</optional>
|
|
157
|
+
<optional>
|
|
158
|
+
<element name="year">
|
|
159
|
+
<text/>
|
|
160
|
+
</element>
|
|
161
|
+
</optional>
|
|
162
|
+
</element>
|
|
163
|
+
</define>
|
|
164
|
+
</grammar>
|
|
@@ -33,9 +33,10 @@
|
|
|
33
33
|
<param name="pattern">([\+\-]?\d{4})((-?)((0[1-9]|1[0-2])((-?)([12]\d|0[1-9]|3[01]))?|W([0-4]\d|5[0-2])(-?[1-7])?|(00[1-9]|0[1-9]\d|[12]\d{2}|3([0-5]\d|6[1-6]))))?</param>
|
|
34
34
|
</data>
|
|
35
35
|
</define>
|
|
36
|
-
|
|
37
|
-
|
|
38
|
-
|
|
36
|
+
<!-- start = bibitem -->
|
|
37
|
+
<define name="BibData">
|
|
38
|
+
<ref name="BibliographicItem"/>
|
|
39
|
+
</define>
|
|
39
40
|
<define name="status">
|
|
40
41
|
<element name="status">
|
|
41
42
|
<ref name="stage"/>
|
|
@@ -170,27 +171,25 @@
|
|
|
170
171
|
</define>
|
|
171
172
|
<define name="contributor">
|
|
172
173
|
<element name="contributor">
|
|
173
|
-
<
|
|
174
|
+
<oneOrMore>
|
|
174
175
|
<ref name="role"/>
|
|
175
|
-
</
|
|
176
|
+
</oneOrMore>
|
|
176
177
|
<ref name="ContributorInfo"/>
|
|
177
178
|
</element>
|
|
178
179
|
</define>
|
|
179
180
|
<define name="role">
|
|
180
181
|
<element name="role">
|
|
181
|
-
<
|
|
182
|
-
<
|
|
183
|
-
<
|
|
184
|
-
|
|
185
|
-
|
|
186
|
-
|
|
187
|
-
|
|
188
|
-
|
|
189
|
-
|
|
190
|
-
|
|
191
|
-
|
|
192
|
-
</attribute>
|
|
193
|
-
</optional>
|
|
182
|
+
<attribute name="type">
|
|
183
|
+
<choice>
|
|
184
|
+
<value>author</value>
|
|
185
|
+
<value>performer</value>
|
|
186
|
+
<value>publisher</value>
|
|
187
|
+
<value>editor</value>
|
|
188
|
+
<value>adapter</value>
|
|
189
|
+
<value>translator</value>
|
|
190
|
+
<value>distributor</value>
|
|
191
|
+
</choice>
|
|
192
|
+
</attribute>
|
|
194
193
|
<zeroOrMore>
|
|
195
194
|
<ref name="roledescription"/>
|
|
196
195
|
</zeroOrMore>
|
|
@@ -512,6 +511,17 @@
|
|
|
512
511
|
</define>
|
|
513
512
|
<define name="localityStack">
|
|
514
513
|
<element name="localityStack">
|
|
514
|
+
<optional>
|
|
515
|
+
<attribute name="connective">
|
|
516
|
+
<choice>
|
|
517
|
+
<value>and</value>
|
|
518
|
+
<value>or</value>
|
|
519
|
+
<value>from</value>
|
|
520
|
+
<value>to</value>
|
|
521
|
+
<value/>
|
|
522
|
+
</choice>
|
|
523
|
+
</attribute>
|
|
524
|
+
</optional>
|
|
515
525
|
<zeroOrMore>
|
|
516
526
|
<ref name="locality"/>
|
|
517
527
|
</zeroOrMore>
|
|
@@ -524,6 +534,17 @@
|
|
|
524
534
|
</define>
|
|
525
535
|
<define name="sourceLocalityStack">
|
|
526
536
|
<element name="sourceLocalityStack">
|
|
537
|
+
<optional>
|
|
538
|
+
<attribute name="connective">
|
|
539
|
+
<choice>
|
|
540
|
+
<value>and</value>
|
|
541
|
+
<value>or</value>
|
|
542
|
+
<value>from</value>
|
|
543
|
+
<value>to</value>
|
|
544
|
+
<value/>
|
|
545
|
+
</choice>
|
|
546
|
+
</attribute>
|
|
547
|
+
</optional>
|
|
527
548
|
<zeroOrMore>
|
|
528
549
|
<ref name="sourceLocality"/>
|
|
529
550
|
</zeroOrMore>
|
|
@@ -626,6 +647,9 @@
|
|
|
626
647
|
<ref name="BibItemType"/>
|
|
627
648
|
</attribute>
|
|
628
649
|
</optional>
|
|
650
|
+
<optional>
|
|
651
|
+
<attribute name="schema-version"/>
|
|
652
|
+
</optional>
|
|
629
653
|
<optional>
|
|
630
654
|
<ref name="fetched"/>
|
|
631
655
|
</optional>
|
|
@@ -720,6 +744,9 @@
|
|
|
720
744
|
<ref name="BibItemType"/>
|
|
721
745
|
</attribute>
|
|
722
746
|
</optional>
|
|
747
|
+
<optional>
|
|
748
|
+
<attribute name="schema-version"/>
|
|
749
|
+
</optional>
|
|
723
750
|
<optional>
|
|
724
751
|
<ref name="fetched"/>
|
|
725
752
|
</optional>
|
|
@@ -5,6 +5,7 @@ require_relative "./cleanup_block"
|
|
|
5
5
|
require_relative "./cleanup_table"
|
|
6
6
|
require_relative "./cleanup_footnotes"
|
|
7
7
|
require_relative "./cleanup_ref"
|
|
8
|
+
require_relative "./cleanup_asciibib"
|
|
8
9
|
require_relative "./cleanup_biblio"
|
|
9
10
|
require_relative "./cleanup_boilerplate"
|
|
10
11
|
require_relative "./cleanup_section"
|
|
@@ -0,0 +1,110 @@
|
|
|
1
|
+
require "set"
|
|
2
|
+
require "relaton_bib"
|
|
3
|
+
|
|
4
|
+
module Metanorma
|
|
5
|
+
module Standoc
|
|
6
|
+
module Cleanup
|
|
7
|
+
def ref_dl_cleanup(xmldoc)
|
|
8
|
+
xmldoc.xpath("//clause[@bibitem = 'true']").each do |c|
|
|
9
|
+
bib = dl_bib_extract(c) or next
|
|
10
|
+
validate_ref_dl(bib, c)
|
|
11
|
+
bibitemxml = RelatonBib::BibliographicItem.from_hash(bib).to_xml or next
|
|
12
|
+
bibitem = Nokogiri::XML(bibitemxml)
|
|
13
|
+
bibitem.root["id"] = c["id"] if c["id"] && !/^_/.match(c["id"])
|
|
14
|
+
c.replace(bibitem.root)
|
|
15
|
+
end
|
|
16
|
+
end
|
|
17
|
+
|
|
18
|
+
# do not accept implicit id
|
|
19
|
+
def validate_ref_dl(bib, clause)
|
|
20
|
+
id = bib["id"]
|
|
21
|
+
id ||= clause["id"] unless /^_/.match?(clause["id"])
|
|
22
|
+
unless id
|
|
23
|
+
@log.add("Anchors", clause,
|
|
24
|
+
"The following reference is missing an anchor:\n" \
|
|
25
|
+
"#{clause.to_xml}")
|
|
26
|
+
return
|
|
27
|
+
end
|
|
28
|
+
@refids << id
|
|
29
|
+
validate_ref_dl1(bib, id, clause)
|
|
30
|
+
end
|
|
31
|
+
|
|
32
|
+
def validate_ref_dl1(bib, id, clause)
|
|
33
|
+
bib["title"] or
|
|
34
|
+
@log.add("Bibliography", clause, "Reference #{id} is missing a title")
|
|
35
|
+
bib["docid"] or
|
|
36
|
+
@log.add("Bibliography", clause,
|
|
37
|
+
"Reference #{id} is missing a document identifier (docid)")
|
|
38
|
+
end
|
|
39
|
+
|
|
40
|
+
def extract_from_p(tag, bib, key)
|
|
41
|
+
return unless bib[tag]
|
|
42
|
+
|
|
43
|
+
"<#{key}>#{bib[tag].at('p').children}</#{key}>"
|
|
44
|
+
end
|
|
45
|
+
|
|
46
|
+
# if the content is a single paragraph, replace it with its children
|
|
47
|
+
# single links replaced with uri
|
|
48
|
+
def p_unwrap(para)
|
|
49
|
+
elems = para.elements
|
|
50
|
+
if elems.size == 1 && elems[0].name == "p"
|
|
51
|
+
link_unwrap(elems[0]).children.to_xml.strip
|
|
52
|
+
else
|
|
53
|
+
para.to_xml.strip
|
|
54
|
+
end
|
|
55
|
+
end
|
|
56
|
+
|
|
57
|
+
def link_unwrap(para)
|
|
58
|
+
elems = para.elements
|
|
59
|
+
if elems.size == 1 && elems[0].name == "link"
|
|
60
|
+
para.at("./link").replace(elems[0]["target"].strip)
|
|
61
|
+
end
|
|
62
|
+
para
|
|
63
|
+
end
|
|
64
|
+
|
|
65
|
+
def dd_bib_extract(dtd)
|
|
66
|
+
return nil if dtd.children.empty?
|
|
67
|
+
|
|
68
|
+
dtd.at("./dl") and return dl_bib_extract(dtd)
|
|
69
|
+
elems = dtd.remove.elements
|
|
70
|
+
return p_unwrap(dtd) unless elems.size == 1 &&
|
|
71
|
+
%w(ol ul).include?(elems[0].name)
|
|
72
|
+
|
|
73
|
+
elems[0].xpath("./li").each_with_object([]) do |li, ret|
|
|
74
|
+
ret << p_unwrap(li)
|
|
75
|
+
end
|
|
76
|
+
end
|
|
77
|
+
|
|
78
|
+
def add_to_hash(bib, key, val)
|
|
79
|
+
Metanorma::Utils::set_nested_value(bib, key.split("."), val)
|
|
80
|
+
end
|
|
81
|
+
|
|
82
|
+
# definition list, with at most one level of unordered lists
|
|
83
|
+
def dl_bib_extract(clause, nested = false)
|
|
84
|
+
dl = clause.at("./dl") or return
|
|
85
|
+
key = ""
|
|
86
|
+
bib = dl.xpath("./dt | ./dd").each_with_object({}) do |dtd, m|
|
|
87
|
+
(dtd.name == "dt" and key = dtd.text.sub(/:+$/, "")) and next
|
|
88
|
+
add_to_hash(m, key, dd_bib_extract(dtd))
|
|
89
|
+
end
|
|
90
|
+
clause.xpath("./clause").each do |c1|
|
|
91
|
+
key = c1&.at("./title")&.text&.downcase&.strip
|
|
92
|
+
next unless %w(contributor relation series).include? key
|
|
93
|
+
|
|
94
|
+
add_to_hash(bib, key, dl_bib_extract(c1, true))
|
|
95
|
+
end
|
|
96
|
+
dl_bib_extract_title(bib, clause, nested)
|
|
97
|
+
end
|
|
98
|
+
|
|
99
|
+
def dl_bib_extract_title(bib, clause, nested)
|
|
100
|
+
(!nested && clause.at("./title")) or return bib
|
|
101
|
+
title = clause.at("./title").remove.children.to_xml
|
|
102
|
+
bib["title"] = [bib["title"]] if bib["title"].is_a?(Hash) ||
|
|
103
|
+
bib["title"].is_a?(String)
|
|
104
|
+
bib["title"] ||= []
|
|
105
|
+
bib["title"] << title if !title.empty?
|
|
106
|
+
bib
|
|
107
|
+
end
|
|
108
|
+
end
|
|
109
|
+
end
|
|
110
|
+
end
|
|
@@ -1,113 +1,6 @@
|
|
|
1
|
-
require "set"
|
|
2
|
-
require "relaton_bib"
|
|
3
|
-
|
|
4
1
|
module Metanorma
|
|
5
2
|
module Standoc
|
|
6
3
|
module Cleanup
|
|
7
|
-
def ref_dl_cleanup(xmldoc)
|
|
8
|
-
xmldoc.xpath("//clause[@bibitem = 'true']").each do |c|
|
|
9
|
-
bib = dl_bib_extract(c) or next
|
|
10
|
-
validate_ref_dl(bib, c)
|
|
11
|
-
bibitemxml = RelatonBib::BibliographicItem.from_hash(bib).to_xml or next
|
|
12
|
-
bibitem = Nokogiri::XML(bibitemxml)
|
|
13
|
-
bibitem.root["id"] = c["id"] if c["id"] && !/^_/.match(c["id"])
|
|
14
|
-
c.replace(bibitem.root)
|
|
15
|
-
end
|
|
16
|
-
end
|
|
17
|
-
|
|
18
|
-
# do not accept implicit id
|
|
19
|
-
def validate_ref_dl(bib, clause)
|
|
20
|
-
id = bib["id"]
|
|
21
|
-
id ||= clause["id"] unless /^_/.match?(clause["id"])
|
|
22
|
-
unless id
|
|
23
|
-
@log.add("Anchors", clause,
|
|
24
|
-
"The following reference is missing an anchor:\n"\
|
|
25
|
-
"#{clause.to_xml}")
|
|
26
|
-
return
|
|
27
|
-
end
|
|
28
|
-
@refids << id
|
|
29
|
-
validate_ref_dl1(bib, id, clause)
|
|
30
|
-
end
|
|
31
|
-
|
|
32
|
-
def validate_ref_dl1(bib, id, clause)
|
|
33
|
-
bib["title"] or
|
|
34
|
-
@log.add("Bibliography", clause, "Reference #{id} is missing a title")
|
|
35
|
-
bib["docid"] or
|
|
36
|
-
@log.add("Bibliography", clause,
|
|
37
|
-
"Reference #{id} is missing a document identifier (docid)")
|
|
38
|
-
end
|
|
39
|
-
|
|
40
|
-
def extract_from_p(tag, bib, key)
|
|
41
|
-
return unless bib[tag]
|
|
42
|
-
|
|
43
|
-
"<#{key}>#{bib[tag].at('p').children}</#{key}>"
|
|
44
|
-
end
|
|
45
|
-
|
|
46
|
-
# if the content is a single paragraph, replace it with its children
|
|
47
|
-
# single links replaced with uri
|
|
48
|
-
def p_unwrap(para)
|
|
49
|
-
elems = para.elements
|
|
50
|
-
if elems.size == 1 && elems[0].name == "p"
|
|
51
|
-
link_unwrap(elems[0]).children.to_xml.strip
|
|
52
|
-
else
|
|
53
|
-
para.to_xml.strip
|
|
54
|
-
end
|
|
55
|
-
end
|
|
56
|
-
|
|
57
|
-
def link_unwrap(para)
|
|
58
|
-
elems = para.elements
|
|
59
|
-
if elems.size == 1 && elems[0].name == "link"
|
|
60
|
-
para.at("./link").replace(elems[0]["target"].strip)
|
|
61
|
-
end
|
|
62
|
-
para
|
|
63
|
-
end
|
|
64
|
-
|
|
65
|
-
def dd_bib_extract(dtd)
|
|
66
|
-
return nil if dtd.children.empty?
|
|
67
|
-
|
|
68
|
-
dtd.at("./dl") and return dl_bib_extract(dtd)
|
|
69
|
-
elems = dtd.remove.elements
|
|
70
|
-
return p_unwrap(dtd) unless elems.size == 1 &&
|
|
71
|
-
%w(ol ul).include?(elems[0].name)
|
|
72
|
-
|
|
73
|
-
elems[0].xpath("./li").each_with_object([]) do |li, ret|
|
|
74
|
-
ret << p_unwrap(li)
|
|
75
|
-
end
|
|
76
|
-
end
|
|
77
|
-
|
|
78
|
-
def add_to_hash(bib, key, val)
|
|
79
|
-
Metanorma::Utils::set_nested_value(bib, key.split("."), val)
|
|
80
|
-
end
|
|
81
|
-
|
|
82
|
-
# definition list, with at most one level of unordered lists
|
|
83
|
-
def dl_bib_extract(clause, nested = false)
|
|
84
|
-
dl = clause.at("./dl") or return
|
|
85
|
-
key = ""
|
|
86
|
-
bib = dl.xpath("./dt | ./dd").each_with_object({}) do |dtd, m|
|
|
87
|
-
(dtd.name == "dt" and key = dtd.text.sub(/:+$/, "")) and next
|
|
88
|
-
add_to_hash(m, key, dd_bib_extract(dtd))
|
|
89
|
-
end
|
|
90
|
-
clause.xpath("./clause").each do |c1|
|
|
91
|
-
key = c1&.at("./title")&.text&.downcase&.strip
|
|
92
|
-
next unless %w(contributor relation series).include? key
|
|
93
|
-
|
|
94
|
-
add_to_hash(bib, key, dl_bib_extract(c1, true))
|
|
95
|
-
end
|
|
96
|
-
dl_bib_extract_title(bib, clause, nested)
|
|
97
|
-
end
|
|
98
|
-
|
|
99
|
-
def dl_bib_extract_title(bib, clause, nested)
|
|
100
|
-
(!nested && clause.at("./title")) or return bib
|
|
101
|
-
title = clause.at("./title").remove.children.to_xml
|
|
102
|
-
bib["title"] = [bib["title"]] if bib["title"].is_a?(Hash) ||
|
|
103
|
-
bib["title"].is_a?(String)
|
|
104
|
-
bib["title"] ||= []
|
|
105
|
-
bib["title"] << title if !title.empty?
|
|
106
|
-
bib
|
|
107
|
-
end
|
|
108
|
-
|
|
109
|
-
# ---
|
|
110
|
-
|
|
111
4
|
def formattedref_spans(xmldoc)
|
|
112
5
|
xmldoc.xpath("//bibitem[formattedref//span]").each do |b|
|
|
113
6
|
spans = spans_preprocess(extract_content(b))
|
|
@@ -263,10 +156,11 @@ module Metanorma
|
|
|
263
156
|
|
|
264
157
|
def span_to_extent(span, key)
|
|
265
158
|
values = span.split(/[-–]/)
|
|
266
|
-
ret = "<extent type='#{key}'><
|
|
159
|
+
ret = "<extent type='#{key}'><locality>" \
|
|
160
|
+
"<referenceFrom>#{values[0]}</referenceFrom>"
|
|
267
161
|
values[1] and
|
|
268
162
|
ret += "<referenceTo>#{values[1]}</referenceTo>"
|
|
269
|
-
"#{ret}</extent>"
|
|
163
|
+
"#{ret}</locality></extent>"
|
|
270
164
|
end
|
|
271
165
|
|
|
272
166
|
def span_to_docid(span, key)
|
|
@@ -287,10 +181,10 @@ module Metanorma
|
|
|
287
181
|
|
|
288
182
|
def span_to_person(span)
|
|
289
183
|
pre = (span[:"formatted-initials"] and
|
|
290
|
-
"<formatted-initials>"\
|
|
184
|
+
"<formatted-initials>" \
|
|
291
185
|
"#{span[:"formatted-initials"]}</formatted-initials>") ||
|
|
292
186
|
"<forename>#{span[:givenname]}</forename>"
|
|
293
|
-
"<person><name>#{pre}<surname>#{span[:surname]}</surname></name>"\
|
|
187
|
+
"<person><name>#{pre}<surname>#{span[:surname]}</surname></name>" \
|
|
294
188
|
"</person>"
|
|
295
189
|
end
|
|
296
190
|
end
|
|
@@ -7,7 +7,8 @@ module Metanorma
|
|
|
7
7
|
def para_cleanup(xmldoc)
|
|
8
8
|
["//p[not(ancestor::bibdata)]", "//ol[not(ancestor::bibdata)]",
|
|
9
9
|
"//ul[not(ancestor::bibdata)]", "//quote[not(ancestor::bibdata)]",
|
|
10
|
-
"//
|
|
10
|
+
"//dl[not(ancestor::bibdata)]",
|
|
11
|
+
"//note[not(ancestor::bibitem or " \
|
|
11
12
|
"ancestor::table or ancestor::bibdata)]"].each do |w|
|
|
12
13
|
inject_id(xmldoc, w)
|
|
13
14
|
end
|
|
@@ -106,7 +107,7 @@ module Metanorma
|
|
|
106
107
|
prev = n.previous_element || next
|
|
107
108
|
n.parent = prev if ELEMS_ALLOW_NOTES.include? prev.name
|
|
108
109
|
end
|
|
109
|
-
xmldoc.xpath("//note[@keep-separate] | "\
|
|
110
|
+
xmldoc.xpath("//note[@keep-separate] | " \
|
|
110
111
|
"//termnote[@keep-separate]").each do |n|
|
|
111
112
|
n.delete("keep-separate")
|
|
112
113
|
end
|
|
@@ -182,10 +183,10 @@ module Metanorma
|
|
|
182
183
|
end
|
|
183
184
|
|
|
184
185
|
def block_index_cleanup(xmldoc)
|
|
185
|
-
xmldoc.xpath("//quote | //td | //th | //formula | //li | //dt | "\
|
|
186
|
-
"//dd | //example | //note | //figure | //sourcecode | "\
|
|
187
|
-
"//admonition | //termnote | //termexample | //form | "\
|
|
188
|
-
"//requirement | //recommendation | //permission | "\
|
|
186
|
+
xmldoc.xpath("//quote | //td | //th | //formula | //li | //dt | " \
|
|
187
|
+
"//dd | //example | //note | //figure | //sourcecode | " \
|
|
188
|
+
"//admonition | //termnote | //termexample | //form | " \
|
|
189
|
+
"//requirement | //recommendation | //permission | " \
|
|
189
190
|
"//imagemap | //svgmap").each do |b|
|
|
190
191
|
b.xpath("./p[indexterm]").each do |p|
|
|
191
192
|
indexterm_para?(p) or next
|