relaton-nist 1.7.4 → 1.9.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.github/workflows/rake.yml +1 -11
- data/.gitignore +1 -0
- data/.rubocop.yml +1 -1
- data/README.adoc +19 -0
- data/bin/rspec +29 -0
- data/grammars/basicdoc.rng +165 -20
- data/grammars/biblio.rng +5 -6
- data/grammars/isodoc.rng +532 -16
- data/grammars/nist.rng +9 -0
- data/grammars/reqt.rng +31 -2
- data/lib/relaton_nist/data_fetcher.rb +221 -0
- data/lib/relaton_nist/hit.rb +3 -1
- data/lib/relaton_nist/hit_collection.rb +71 -58
- data/lib/relaton_nist/nist_bibliographic_item.rb +1 -1
- data/lib/relaton_nist/nist_bibliography.rb +16 -6
- data/lib/relaton_nist/processor.rb +5 -0
- data/lib/relaton_nist/scrapper.rb +198 -265
- data/lib/relaton_nist/version.rb +1 -1
- data/lib/relaton_nist/xml_parser.rb +1 -1
- data/lib/relaton_nist.rb +1 -0
- data/relaton_nist.gemspec +3 -5
- metadata +9 -7
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 76cfec1954dfd58bf622a6a47e34bdbcfe4cf471106eb7ad19582654078a6d38
|
|
4
|
+
data.tar.gz: 9769f406d5b98840b5bc099d78ab811388170d1fae5872211a7a0c9ed26d869f
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 0e3deefff699c77103afb631a03283697dc05f5c952b60b3602961df37df2095102b16c32e229aeeceb76da12cfda09e43e6b0788b6a4c1f02b74dea8a49f818
|
|
7
|
+
data.tar.gz: 3244707d2595b5b45bab973399a04b8cc791d3b008e2ef05fcc99d9355cec6915556aea8528e5f992e4ba0452af82bda09fb93737741a72c08a64e7a0039d161
|
data/.github/workflows/rake.yml
CHANGED
|
@@ -16,19 +16,9 @@ jobs:
|
|
|
16
16
|
strategy:
|
|
17
17
|
fail-fast: false
|
|
18
18
|
matrix:
|
|
19
|
-
ruby: [ '
|
|
19
|
+
ruby: [ '3.0', '2.7', '2.6', '2.5' ]
|
|
20
20
|
os: [ ubuntu-latest, windows-latest, macos-latest ]
|
|
21
21
|
experimental: [ false ]
|
|
22
|
-
include:
|
|
23
|
-
- ruby: '3.0'
|
|
24
|
-
os: 'ubuntu-latest'
|
|
25
|
-
experimental: true
|
|
26
|
-
- ruby: '3.0'
|
|
27
|
-
os: 'windows-latest'
|
|
28
|
-
experimental: true
|
|
29
|
-
- ruby: '3.0'
|
|
30
|
-
os: 'macos-latest'
|
|
31
|
-
experimental: true
|
|
32
22
|
steps:
|
|
33
23
|
- uses: actions/checkout@v2
|
|
34
24
|
with:
|
data/.gitignore
CHANGED
data/.rubocop.yml
CHANGED
data/README.adoc
CHANGED
|
@@ -159,6 +159,25 @@ RelatonNist::NistBibliographicItem.from_hash hash
|
|
|
159
159
|
...
|
|
160
160
|
----
|
|
161
161
|
|
|
162
|
+
=== Fetch data
|
|
163
|
+
|
|
164
|
+
This gem uses the https://raw.githubusercontent.com/usnistgov/NIST-Tech-Pubs/nist-pages/xml/allrecords.xml dataset as one of data sources.
|
|
165
|
+
|
|
166
|
+
The method `RelatonNist::DataFetcher.fetch(output: "data", format: "yaml")` fetches all the documents from the datast and save them to the `./data` folder in YAML format.
|
|
167
|
+
Arguments:
|
|
168
|
+
|
|
169
|
+
- `output` - folder to save documents (default './data').
|
|
170
|
+
- `format` - format in which the documents are saved. Possimle formats are: `yaml`, `xml` (default `yaml`).
|
|
171
|
+
|
|
172
|
+
[source,ruby]
|
|
173
|
+
----
|
|
174
|
+
RelatonNist::DataFetcher.fetch
|
|
175
|
+
Started at: 2021-09-01 18:01:01 +0200
|
|
176
|
+
Stopped at: 2021-09-01 18:01:43 +0200
|
|
177
|
+
Done in: 42 sec.
|
|
178
|
+
=> nil
|
|
179
|
+
----
|
|
180
|
+
|
|
162
181
|
== Development
|
|
163
182
|
|
|
164
183
|
After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
|
data/bin/rspec
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
1
|
+
#!/usr/bin/env ruby
|
|
2
|
+
# frozen_string_literal: true
|
|
3
|
+
|
|
4
|
+
#
|
|
5
|
+
# This file was generated by Bundler.
|
|
6
|
+
#
|
|
7
|
+
# The application 'rspec' is installed as part of a gem, and
|
|
8
|
+
# this file is here to facilitate running it.
|
|
9
|
+
#
|
|
10
|
+
|
|
11
|
+
require "pathname"
|
|
12
|
+
ENV["BUNDLE_GEMFILE"] ||= File.expand_path("../../Gemfile",
|
|
13
|
+
Pathname.new(__FILE__).realpath)
|
|
14
|
+
|
|
15
|
+
bundle_binstub = File.expand_path("../bundle", __FILE__)
|
|
16
|
+
|
|
17
|
+
if File.file?(bundle_binstub)
|
|
18
|
+
if File.read(bundle_binstub, 300) =~ /This file was generated by Bundler/
|
|
19
|
+
load(bundle_binstub)
|
|
20
|
+
else
|
|
21
|
+
abort("Your `bin/bundle` was not generated by Bundler, so this binstub cannot run.
|
|
22
|
+
Replace `bin/bundle` by running `bundle binstubs bundler --force`, then run this command again.")
|
|
23
|
+
end
|
|
24
|
+
end
|
|
25
|
+
|
|
26
|
+
require "rubygems"
|
|
27
|
+
require "bundler/setup"
|
|
28
|
+
|
|
29
|
+
load Gem.bin_path("rspec-core", "rspec")
|
data/grammars/basicdoc.rng
CHANGED
|
@@ -1,9 +1,10 @@
|
|
|
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
|
-
|
|
5
|
-
|
|
6
|
-
|
|
3
|
+
<include href="biblio.rng">
|
|
4
|
+
<start>
|
|
5
|
+
<ref name="document"/>
|
|
6
|
+
</start>
|
|
7
|
+
</include>
|
|
7
8
|
<define name="document">
|
|
8
9
|
<element name="document">
|
|
9
10
|
<optional>
|
|
@@ -43,13 +44,16 @@
|
|
|
43
44
|
</attribute>
|
|
44
45
|
</optional>
|
|
45
46
|
<optional>
|
|
46
|
-
<
|
|
47
|
+
<attribute name="language"/>
|
|
47
48
|
</optional>
|
|
48
49
|
<optional>
|
|
49
|
-
<
|
|
50
|
+
<attribute name="script"/>
|
|
51
|
+
</optional>
|
|
52
|
+
<optional>
|
|
53
|
+
<ref name="section-title"/>
|
|
50
54
|
</optional>
|
|
51
55
|
<zeroOrMore>
|
|
52
|
-
<ref name="
|
|
56
|
+
<ref name="BasicBlock"/>
|
|
53
57
|
</zeroOrMore>
|
|
54
58
|
</define>
|
|
55
59
|
<define name="references">
|
|
@@ -92,6 +96,10 @@
|
|
|
92
96
|
<ref name="example"/>
|
|
93
97
|
<ref name="review"/>
|
|
94
98
|
<ref name="pre"/>
|
|
99
|
+
<ref name="note"/>
|
|
100
|
+
<ref name="pagebreak"/>
|
|
101
|
+
<ref name="hr"/>
|
|
102
|
+
<ref name="bookmark"/>
|
|
95
103
|
</choice>
|
|
96
104
|
</define>
|
|
97
105
|
<define name="paragraph">
|
|
@@ -188,6 +196,14 @@
|
|
|
188
196
|
<data type="boolean"/>
|
|
189
197
|
</attribute>
|
|
190
198
|
</optional>
|
|
199
|
+
<optional>
|
|
200
|
+
<attribute name="subsequence"/>
|
|
201
|
+
</optional>
|
|
202
|
+
<optional>
|
|
203
|
+
<attribute name="inequality">
|
|
204
|
+
<data type="boolean"/>
|
|
205
|
+
</attribute>
|
|
206
|
+
</optional>
|
|
191
207
|
<ref name="stem"/>
|
|
192
208
|
<optional>
|
|
193
209
|
<ref name="dl"/>
|
|
@@ -241,6 +257,9 @@
|
|
|
241
257
|
<data type="boolean"/>
|
|
242
258
|
</attribute>
|
|
243
259
|
</optional>
|
|
260
|
+
<optional>
|
|
261
|
+
<attribute name="subsequence"/>
|
|
262
|
+
</optional>
|
|
244
263
|
<optional>
|
|
245
264
|
<attribute name="lang"/>
|
|
246
265
|
</optional>
|
|
@@ -266,6 +285,9 @@
|
|
|
266
285
|
<attribute name="id">
|
|
267
286
|
<data type="ID"/>
|
|
268
287
|
</attribute>
|
|
288
|
+
<optional>
|
|
289
|
+
<attribute name="alt"/>
|
|
290
|
+
</optional>
|
|
269
291
|
<optional>
|
|
270
292
|
<ref name="tname"/>
|
|
271
293
|
</optional>
|
|
@@ -285,9 +307,15 @@
|
|
|
285
307
|
<data type="boolean"/>
|
|
286
308
|
</attribute>
|
|
287
309
|
</optional>
|
|
310
|
+
<optional>
|
|
311
|
+
<attribute name="subsequence"/>
|
|
312
|
+
</optional>
|
|
288
313
|
<optional>
|
|
289
314
|
<attribute name="alt"/>
|
|
290
315
|
</optional>
|
|
316
|
+
<optional>
|
|
317
|
+
<attribute name="summary"/>
|
|
318
|
+
</optional>
|
|
291
319
|
<optional>
|
|
292
320
|
<attribute name="uri">
|
|
293
321
|
<data type="anyURI"/>
|
|
@@ -313,12 +341,16 @@
|
|
|
313
341
|
</define>
|
|
314
342
|
<define name="tname">
|
|
315
343
|
<element name="name">
|
|
316
|
-
<
|
|
317
|
-
|
|
318
|
-
|
|
319
|
-
|
|
320
|
-
|
|
321
|
-
|
|
344
|
+
<oneOrMore>
|
|
345
|
+
<choice>
|
|
346
|
+
<ref name="PureTextElement"/>
|
|
347
|
+
<ref name="eref"/>
|
|
348
|
+
<ref name="stem"/>
|
|
349
|
+
<ref name="keyword"/>
|
|
350
|
+
<ref name="xref"/>
|
|
351
|
+
<ref name="hyperlink"/>
|
|
352
|
+
</choice>
|
|
353
|
+
</oneOrMore>
|
|
322
354
|
</element>
|
|
323
355
|
</define>
|
|
324
356
|
<define name="thead">
|
|
@@ -370,6 +402,16 @@
|
|
|
370
402
|
</choice>
|
|
371
403
|
</attribute>
|
|
372
404
|
</optional>
|
|
405
|
+
<optional>
|
|
406
|
+
<attribute name="valign">
|
|
407
|
+
<choice>
|
|
408
|
+
<value>top</value>
|
|
409
|
+
<value>middle</value>
|
|
410
|
+
<value>bottom</value>
|
|
411
|
+
<value>baseline</value>
|
|
412
|
+
</choice>
|
|
413
|
+
</attribute>
|
|
414
|
+
</optional>
|
|
373
415
|
<choice>
|
|
374
416
|
<zeroOrMore>
|
|
375
417
|
<ref name="TextElement"/>
|
|
@@ -397,6 +439,16 @@
|
|
|
397
439
|
</choice>
|
|
398
440
|
</attribute>
|
|
399
441
|
</optional>
|
|
442
|
+
<optional>
|
|
443
|
+
<attribute name="valign">
|
|
444
|
+
<choice>
|
|
445
|
+
<value>top</value>
|
|
446
|
+
<value>middle</value>
|
|
447
|
+
<value>bottom</value>
|
|
448
|
+
<value>baseline</value>
|
|
449
|
+
</choice>
|
|
450
|
+
</attribute>
|
|
451
|
+
</optional>
|
|
400
452
|
<choice>
|
|
401
453
|
<zeroOrMore>
|
|
402
454
|
<ref name="TextElement"/>
|
|
@@ -417,6 +469,12 @@
|
|
|
417
469
|
<data type="boolean"/>
|
|
418
470
|
</attribute>
|
|
419
471
|
</optional>
|
|
472
|
+
<optional>
|
|
473
|
+
<attribute name="subsequence"/>
|
|
474
|
+
</optional>
|
|
475
|
+
<optional>
|
|
476
|
+
<ref name="tname"/>
|
|
477
|
+
</optional>
|
|
420
478
|
<oneOrMore>
|
|
421
479
|
<choice>
|
|
422
480
|
<ref name="formula"/>
|
|
@@ -481,17 +539,25 @@
|
|
|
481
539
|
</attribute>
|
|
482
540
|
</optional>
|
|
483
541
|
<optional>
|
|
484
|
-
<
|
|
542
|
+
<attribute name="subsequence"/>
|
|
485
543
|
</optional>
|
|
486
544
|
<optional>
|
|
487
|
-
<
|
|
545
|
+
<attribute name="class"/>
|
|
488
546
|
</optional>
|
|
489
547
|
<optional>
|
|
490
|
-
<ref name="
|
|
548
|
+
<ref name="source"/>
|
|
549
|
+
</optional>
|
|
550
|
+
<optional>
|
|
551
|
+
<ref name="tname"/>
|
|
491
552
|
</optional>
|
|
492
553
|
<choice>
|
|
493
554
|
<ref name="image"/>
|
|
555
|
+
<ref name="video"/>
|
|
556
|
+
<ref name="audio"/>
|
|
494
557
|
<ref name="pre"/>
|
|
558
|
+
<oneOrMore>
|
|
559
|
+
<ref name="paragraph-with-footnote"/>
|
|
560
|
+
</oneOrMore>
|
|
495
561
|
<zeroOrMore>
|
|
496
562
|
<ref name="figure"/>
|
|
497
563
|
</zeroOrMore>
|
|
@@ -529,6 +595,8 @@
|
|
|
529
595
|
<ref name="pagebreak"/>
|
|
530
596
|
<ref name="bookmark"/>
|
|
531
597
|
<ref name="image"/>
|
|
598
|
+
<ref name="index"/>
|
|
599
|
+
<ref name="index-xref"/>
|
|
532
600
|
</choice>
|
|
533
601
|
</define>
|
|
534
602
|
<define name="PureTextElement">
|
|
@@ -553,14 +621,20 @@
|
|
|
553
621
|
<define name="em">
|
|
554
622
|
<element name="em">
|
|
555
623
|
<zeroOrMore>
|
|
556
|
-
<
|
|
624
|
+
<choice>
|
|
625
|
+
<ref name="PureTextElement"/>
|
|
626
|
+
<ref name="stem"/>
|
|
627
|
+
</choice>
|
|
557
628
|
</zeroOrMore>
|
|
558
629
|
</element>
|
|
559
630
|
</define>
|
|
560
631
|
<define name="strong">
|
|
561
632
|
<element name="strong">
|
|
562
633
|
<zeroOrMore>
|
|
563
|
-
<
|
|
634
|
+
<choice>
|
|
635
|
+
<ref name="PureTextElement"/>
|
|
636
|
+
<ref name="stem"/>
|
|
637
|
+
</choice>
|
|
564
638
|
</zeroOrMore>
|
|
565
639
|
</element>
|
|
566
640
|
</define>
|
|
@@ -653,6 +727,65 @@
|
|
|
653
727
|
<empty/>
|
|
654
728
|
</element>
|
|
655
729
|
</define>
|
|
730
|
+
<define name="index">
|
|
731
|
+
<element name="index">
|
|
732
|
+
<optional>
|
|
733
|
+
<attribute name="to">
|
|
734
|
+
<data type="IDREF"/>
|
|
735
|
+
</attribute>
|
|
736
|
+
</optional>
|
|
737
|
+
<element name="primary">
|
|
738
|
+
<oneOrMore>
|
|
739
|
+
<ref name="PureTextElement"/>
|
|
740
|
+
</oneOrMore>
|
|
741
|
+
</element>
|
|
742
|
+
<optional>
|
|
743
|
+
<element name="secondary">
|
|
744
|
+
<oneOrMore>
|
|
745
|
+
<ref name="PureTextElement"/>
|
|
746
|
+
</oneOrMore>
|
|
747
|
+
</element>
|
|
748
|
+
</optional>
|
|
749
|
+
<optional>
|
|
750
|
+
<element name="tertiary">
|
|
751
|
+
<oneOrMore>
|
|
752
|
+
<ref name="PureTextElement"/>
|
|
753
|
+
</oneOrMore>
|
|
754
|
+
</element>
|
|
755
|
+
</optional>
|
|
756
|
+
</element>
|
|
757
|
+
</define>
|
|
758
|
+
<define name="index-xref">
|
|
759
|
+
<element name="index-xref">
|
|
760
|
+
<attribute name="also">
|
|
761
|
+
<data type="boolean"/>
|
|
762
|
+
</attribute>
|
|
763
|
+
<element name="primary">
|
|
764
|
+
<oneOrMore>
|
|
765
|
+
<ref name="PureTextElement"/>
|
|
766
|
+
</oneOrMore>
|
|
767
|
+
</element>
|
|
768
|
+
<optional>
|
|
769
|
+
<element name="secondary">
|
|
770
|
+
<oneOrMore>
|
|
771
|
+
<ref name="PureTextElement"/>
|
|
772
|
+
</oneOrMore>
|
|
773
|
+
</element>
|
|
774
|
+
</optional>
|
|
775
|
+
<optional>
|
|
776
|
+
<element name="tertiary">
|
|
777
|
+
<oneOrMore>
|
|
778
|
+
<ref name="PureTextElement"/>
|
|
779
|
+
</oneOrMore>
|
|
780
|
+
</element>
|
|
781
|
+
</optional>
|
|
782
|
+
<element name="target">
|
|
783
|
+
<oneOrMore>
|
|
784
|
+
<ref name="PureTextElement"/>
|
|
785
|
+
</oneOrMore>
|
|
786
|
+
</element>
|
|
787
|
+
</element>
|
|
788
|
+
</define>
|
|
656
789
|
<!-- bare ID element, used for referencing arbitrary spans of text -->
|
|
657
790
|
<define name="bookmark">
|
|
658
791
|
<element name="bookmark">
|
|
@@ -778,6 +911,9 @@
|
|
|
778
911
|
<optional>
|
|
779
912
|
<attribute name="alt"/>
|
|
780
913
|
</optional>
|
|
914
|
+
<optional>
|
|
915
|
+
<attribute name="title"/>
|
|
916
|
+
</optional>
|
|
781
917
|
<optional>
|
|
782
918
|
<attribute name="longdesc">
|
|
783
919
|
<data type="anyURI"/>
|
|
@@ -786,7 +922,7 @@
|
|
|
786
922
|
</element>
|
|
787
923
|
</define>
|
|
788
924
|
<define name="video">
|
|
789
|
-
<element name="
|
|
925
|
+
<element name="video">
|
|
790
926
|
<attribute name="id">
|
|
791
927
|
<data type="ID"/>
|
|
792
928
|
</attribute>
|
|
@@ -816,6 +952,9 @@
|
|
|
816
952
|
<optional>
|
|
817
953
|
<attribute name="alt"/>
|
|
818
954
|
</optional>
|
|
955
|
+
<optional>
|
|
956
|
+
<attribute name="title"/>
|
|
957
|
+
</optional>
|
|
819
958
|
<optional>
|
|
820
959
|
<attribute name="longdesc">
|
|
821
960
|
<data type="anyURI"/>
|
|
@@ -827,7 +966,7 @@
|
|
|
827
966
|
</element>
|
|
828
967
|
</define>
|
|
829
968
|
<define name="audio">
|
|
830
|
-
<element name="
|
|
969
|
+
<element name="audio">
|
|
831
970
|
<attribute name="id">
|
|
832
971
|
<data type="ID"/>
|
|
833
972
|
</attribute>
|
|
@@ -841,6 +980,9 @@
|
|
|
841
980
|
<optional>
|
|
842
981
|
<attribute name="alt"/>
|
|
843
982
|
</optional>
|
|
983
|
+
<optional>
|
|
984
|
+
<attribute name="title"/>
|
|
985
|
+
</optional>
|
|
844
986
|
<optional>
|
|
845
987
|
<attribute name="longdesc">
|
|
846
988
|
<data type="anyURI"/>
|
|
@@ -925,6 +1067,9 @@
|
|
|
925
1067
|
<value>alphabet_upper</value>
|
|
926
1068
|
</choice>
|
|
927
1069
|
</attribute>
|
|
1070
|
+
<optional>
|
|
1071
|
+
<attribute name="start"/>
|
|
1072
|
+
</optional>
|
|
928
1073
|
<oneOrMore>
|
|
929
1074
|
<ref name="li"/>
|
|
930
1075
|
</oneOrMore>
|