Skip to content

Commit 89f7697

Browse files
TomazErjavecTomazErjavec
committed
Add relevant text from Parla-CLARIN.
1 parent 526de71 commit 89f7697

File tree

8 files changed

+3896
-2294
lines changed

8 files changed

+3896
-2294
lines changed

‎README.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -6,4 +6,4 @@ The preferred TEI schema for language resources deposited in the
66
* top directory contains the TEI ODD schema and example XML file
77
* the schema/ directory contains the Roma-generated XML schemas in RelaxNG, W3C schema, and DTD
88
* the docs/ directory contains the Roma-generated tagset documentation in various formats with the
9-
HTML available through [GutHub pages](https://clarinsi.github.io/TEI-schema/)
9+
HTML available through [GitHub pages](https://clarinsi.github.io/TEI-schema/).

‎docs/tei_clarin_doc.html‎

Lines changed: 2278 additions & 1446 deletions
Large diffs are not rendered by default.

‎schema/tei_clarin.dtd‎

Lines changed: 21 additions & 37 deletions
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11

22
<!--
3-
DTD generated from ODD source 2021-01-21T16:40:13Z. .This file is freely available and you are hereby authorised to copy, modify, and redistribute it in any way without further reference or permissions.
3+
DTD generated from ODD source 2021-08-24T14:19:37Z. .This file is freely available and you are hereby authorised to copy, modify, and redistribute it in any way without further reference or permissions.
44
TEI Edition: Version 4.1.0. Last updated on
55
19th August 2020, revision b414ba550
66
TEI Edition Location: https://www.tei-c.org/Vault/P5/Version 4.1.0/
@@ -670,11 +670,11 @@ to %teidata.word; #IMPLIED'>
670670
<!ENTITY % model.egLike_sequenceOptional "">
671671
<!ENTITY % model.egLike_sequenceOptionalRepeatable "">
672672
<!ENTITY % model.egLike_sequenceRepeatable "">
673-
<!ENTITY % model.graphicLike "media |graphic |binaryObject |formula">
674-
<!ENTITY % model.graphicLike_sequence "media, graphic, binaryObject, formula">
675-
<!ENTITY % model.graphicLike_sequenceOptional "media?, graphic?, binaryObject?, formula?">
676-
<!ENTITY % model.graphicLike_sequenceOptionalRepeatable "media*, graphic*, binaryObject*, formula*">
677-
<!ENTITY % model.graphicLike_sequenceRepeatable "media+, graphic+, binaryObject+, formula+">
673+
<!ENTITY % model.graphicLike "media |graphic |formula">
674+
<!ENTITY % model.graphicLike_sequence "media, graphic, formula">
675+
<!ENTITY % model.graphicLike_sequenceOptional "media?, graphic?, formula?">
676+
<!ENTITY % model.graphicLike_sequenceOptionalRepeatable "media*, graphic*, formula*">
677+
<!ENTITY % model.graphicLike_sequenceRepeatable "media+, graphic+, formula+">
678678
<!ENTITY % model.offsetLike "offset |geogFeat">
679679
<!ENTITY % model.offsetLike_sequence "offset, geogFeat">
680680
<!ENTITY % model.offsetLike_sequenceOptional "offset?, geogFeat?">
@@ -685,11 +685,11 @@ to %teidata.word; #IMPLIED'>
685685
<!ENTITY % model.pPart.msdesc_sequenceOptional "">
686686
<!ENTITY % model.pPart.msdesc_sequenceOptionalRepeatable "">
687687
<!ENTITY % model.pPart.msdesc_sequenceRepeatable "">
688-
<!ENTITY % model.pPart.editorial "choice |abbr |expan |ex |am |subst">
689-
<!ENTITY % model.pPart.editorial_sequence "choice, abbr, expan, ex, am, subst">
690-
<!ENTITY % model.pPart.editorial_sequenceOptional "choice?, abbr?, expan?, ex?, am?, subst?">
691-
<!ENTITY % model.pPart.editorial_sequenceOptionalRepeatable "choice*, abbr*, expan*, ex*, am*, subst*">
692-
<!ENTITY % model.pPart.editorial_sequenceRepeatable "choice+, abbr+, expan+, ex+, am+, subst+">
688+
<!ENTITY % model.pPart.editorial "choice |abbr |expan |ex |subst">
689+
<!ENTITY % model.pPart.editorial_sequence "choice, abbr, expan, ex, subst">
690+
<!ENTITY % model.pPart.editorial_sequenceOptional "choice?, abbr?, expan?, ex?, subst?">
691+
<!ENTITY % model.pPart.editorial_sequenceOptionalRepeatable "choice*, abbr*, expan*, ex*, subst*">
692+
<!ENTITY % model.pPart.editorial_sequenceRepeatable "choice+, abbr+, expan+, ex+, subst+">
693693
<!ENTITY % model.pPart.transcriptional "sic |corr |reg |orig |add |del |unclear |damage |handShift |restore |supplied |surplus |secl |mod |redo |retrace |undo">
694694
<!ENTITY % model.pPart.transcriptional_sequence "sic, corr, reg, orig, add, del, unclear, damage, handShift, restore, supplied, surplus, secl, mod, redo, retrace, undo">
695695
<!ENTITY % model.pPart.transcriptional_sequenceOptional "sic?, corr?, reg?, orig?, add?, del?, unclear?, damage?, handShift?, restore?, supplied?, surplus?, secl?, mod?, redo?, retrace?, undo?">
@@ -930,16 +930,16 @@ to %teidata.word; #IMPLIED'>
930930
<!ENTITY % model.divBottom_sequenceOptional "%model.divWrapper;?, %model.divBottomPart;?">
931931
<!ENTITY % model.divBottom_sequenceOptionalRepeatable "%model.divWrapper;*, %model.divBottomPart;*">
932932
<!ENTITY % model.divBottom_sequenceRepeatable "%model.divWrapper;+, %model.divBottomPart;+">
933-
<!ENTITY % model.titlepagePart "graphic |binaryObject |byline |docTitle |titlePart |docAuthor |imprimatur |docEdition |docImprint |docDate">
934-
<!ENTITY % model.titlepagePart_sequence "graphic, binaryObject, byline, docTitle, titlePart, docAuthor, imprimatur, docEdition, docImprint, docDate">
935-
<!ENTITY % model.titlepagePart_sequenceOptional "graphic?, binaryObject?, byline?, docTitle?, titlePart?, docAuthor?, imprimatur?, docEdition?, docImprint?, docDate?">
936-
<!ENTITY % model.titlepagePart_sequenceOptionalRepeatable "graphic*, binaryObject*, byline*, docTitle*, titlePart*, docAuthor*, imprimatur*, docEdition*, docImprint*, docDate*">
937-
<!ENTITY % model.titlepagePart_sequenceRepeatable "graphic+, binaryObject+, byline+, docTitle+, titlePart+, docAuthor+, imprimatur+, docEdition+, docImprint+, docDate+">
938-
<!ENTITY % model.choicePart "sic |corr |reg |orig |unclear |abbr |expan |ex |am |supplied |seg">
939-
<!ENTITY % model.choicePart_sequence "sic, corr, reg, orig, unclear, abbr, expan, ex, am, supplied, seg">
940-
<!ENTITY % model.choicePart_sequenceOptional "sic?, corr?, reg?, orig?, unclear?, abbr?, expan?, ex?, am?, supplied?, seg?">
941-
<!ENTITY % model.choicePart_sequenceOptionalRepeatable "sic*, corr*, reg*, orig*, unclear*, abbr*, expan*, ex*, am*, supplied*, seg*">
942-
<!ENTITY % model.choicePart_sequenceRepeatable "sic+, corr+, reg+, orig+, unclear+, abbr+, expan+, ex+, am+, supplied+, seg+">
933+
<!ENTITY % model.titlepagePart "graphic |byline |docTitle |titlePart |docAuthor |imprimatur |docEdition |docImprint |docDate">
934+
<!ENTITY % model.titlepagePart_sequence "graphic, byline, docTitle, titlePart, docAuthor, imprimatur, docEdition, docImprint, docDate">
935+
<!ENTITY % model.titlepagePart_sequenceOptional "graphic?, byline?, docTitle?, titlePart?, docAuthor?, imprimatur?, docEdition?, docImprint?, docDate?">
936+
<!ENTITY % model.titlepagePart_sequenceOptionalRepeatable "graphic*, byline*, docTitle*, titlePart*, docAuthor*, imprimatur*, docEdition*, docImprint*, docDate*">
937+
<!ENTITY % model.titlepagePart_sequenceRepeatable "graphic+, byline+, docTitle+, titlePart+, docAuthor+, imprimatur+, docEdition+, docImprint+, docDate+">
938+
<!ENTITY % model.choicePart "sic |corr |reg |orig |unclear |abbr |expan |ex |supplied |seg">
939+
<!ENTITY % model.choicePart_sequence "sic, corr, reg, orig, unclear, abbr, expan, ex, supplied, seg">
940+
<!ENTITY % model.choicePart_sequenceOptional "sic?, corr?, reg?, orig?, unclear?, abbr?, expan?, ex?, supplied?, seg?">
941+
<!ENTITY % model.choicePart_sequenceOptionalRepeatable "sic*, corr*, reg*, orig*, unclear*, abbr*, expan*, ex*, supplied*, seg*">
942+
<!ENTITY % model.choicePart_sequenceRepeatable "sic+, corr+, reg+, orig+, unclear+, abbr+, expan+, ex+, supplied+, seg+">
943943
<!ENTITY % model.imprintPart "publisher |biblScope |pubPlace |distributor">
944944
<!ENTITY % model.imprintPart_sequence "publisher, biblScope, pubPlace, distributor">
945945
<!ENTITY % model.imprintPart_sequenceOptional "publisher?, biblScope?, pubPlace?, distributor?">
@@ -1527,13 +1527,6 @@ weights CDATA #IMPLIED >
15271527
%tei_att.global.attributes;
15281528
%tei_att.pointing.group.attributes;
15291529
mode (excl|incl) "excl" >
1530-
<!--doc:(abbreviation marker) contains a sequence of letters or signs present in an abbreviation which are omitted or replaced in the expanded form of the abbreviation. [11.3.1.2. Abbreviation and Expansion] -->
1531-
<!ELEMENT am (#PCDATA|%model.gLike;|%model.pPart.transcriptional;)*>
1532-
<!ATTLIST am xmlns CDATA "http://www.tei-c.org/ns/1.0">
1533-
<!ATTLIST am
1534-
%tei_att.global.attributes;
1535-
%tei_att.typed.attributes;
1536-
%tei_att.editLike.attributes; >
15371530
<!--doc:(analytic level) contains bibliographic elements describing an item (e.g. an article or poem) published within a monograph or journal and not as an independent publication. [3.11.2.1. Analytic, Monographic, and Series Levels] -->
15381531
<!ELEMENT analytic (author|editor|respStmt|title|%model.ptrLike;|date|textLang|idno|availability)*>
15391532
<!ATTLIST analytic xmlns CDATA "http://www.tei-c.org/ns/1.0">
@@ -1661,15 +1654,6 @@ Feature Value] -->
16611654
%tei_att.global.attributes;
16621655
%tei_att.datcat.attributes;
16631656
value %teidata.truthValue; #REQUIRED >
1664-
<!--doc:provides encoded binary data representing an inline graphic, audio, video or other object. [3.9. Graphics and Other Non-textual Components] -->
1665-
<!ELEMENT binaryObject (#PCDATA)>
1666-
<!ATTLIST binaryObject xmlns CDATA "http://www.tei-c.org/ns/1.0">
1667-
<!ATTLIST binaryObject
1668-
%tei_att.global.attributes;
1669-
%tei_att.media.attributes;
1670-
%tei_att.timed.attributes;
1671-
%tei_att.typed.attributes;
1672-
encoding CDATA #IMPLIED >
16731657
<!--doc:contains information about a person's birth, such as its date and place. [15.2.2. The Participant Description] -->
16741658
<!ELEMENT birth %macro.phraseSeq;>
16751659
<!ATTLIST birth xmlns CDATA "http://www.tei-c.org/ns/1.0">

‎schema/tei_clarin.rnc‎

Lines changed: 28 additions & 66 deletions
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,6 @@
11
namespace a = "http://relaxng.org/ns/compatibility/annotations/1.0"
2+
namespace eg = "http://www.tei-c.org/ns/Examples"
3+
namespace egXML = "http://www.tei-c.org/ns/Examples"
24
namespace ns1 = "http://www.w3.org/1999/xhtml"
35
namespace ns2 = "http://www.isocat.org/ns/dcr"
46
namespace rng = "http://relaxng.org/ns/structure/1.0"
@@ -7,8 +9,9 @@ default namespace tei = "http://www.tei-c.org/ns/1.0"
79
namespace teix = "http://www.tei-c.org/ns/Examples"
810
namespace xi = "http://www.w3.org/2001/XInclude"
911
namespace xlink = "http://www.w3.org/1999/xlink"
12+
namespace xsl = "http://www.w3.org/1999/XSL/Transform"
1013

11-
# Schema generated from ODD source 2021-01-21T16:40:08Z. .
14+
# Schema generated from ODD source 2021-08-24T14:19:32Z. .
1215
# TEI Edition: Version 4.1.0. Last updated on
1316
# 19th August 2020, revision b414ba550
1417
# TEI Edition Location: https://www.tei-c.org/Vault/P5/Version 4.1.0/
@@ -42,7 +45,7 @@ tei_macro.specialPara =
4245
| tei_model.global)*
4346
tei_macro.xtext = (text | tei_model.gLike)*
4447
anyElement-xenoData =
45-
element * - (tei:* | teix:egXML) {
48+
element * - (tei:* | egXML:egXML) {
4649
attribute * { text }*,
4750
(text | anyElement-xenoData)*
4851
}
@@ -338,7 +341,7 @@ sch:pattern [
338341
sch:rule [
339342
context = "tei:*[@when]"
340343
"\x{a}" ~
341-
" "
344+
" "
342345
sch:report [
343346
test = "@notBefore|@notAfter|@from|@to"
344347
role = "nonfatal"
@@ -358,7 +361,7 @@ sch:pattern [
358361
sch:rule [
359362
context = "tei:*[@from]"
360363
"\x{a}" ~
361-
" "
364+
" "
362365
sch:report [
363366
test = "@notBefore"
364367
role = "nonfatal"
@@ -377,7 +380,7 @@ sch:pattern [
377380
sch:rule [
378381
context = "tei:*[@to]"
379382
"\x{a}" ~
380-
" "
383+
" "
381384
sch:report [
382385
test = "@notAfter"
383386
role = "nonfatal"
@@ -406,7 +409,7 @@ sch:pattern [
406409
sch:rule [
407410
context = "tei:*[@calendar]"
408411
"\x{a}" ~
409-
" "
412+
" "
410413
sch:assert [
411414
test = "string-length(.) gt 0"
412415
" @calendar indicates the system or calendar to\x{a}" ~
@@ -416,7 +419,7 @@ sch:pattern [
416419
" element has no textual content."
417420
]
418421
"\x{a}" ~
419-
" "
422+
" "
420423
]
421424
"\x{a}" ~
422425
" "
@@ -894,7 +897,7 @@ sch:pattern [
894897
sch:rule [
895898
context = "tei:*[@unitRef]"
896899
"\x{a}" ~
897-
" "
900+
" "
898901
sch:report [
899902
test = "@unit"
900903
role = "info"
@@ -992,7 +995,7 @@ sch:pattern [
992995
sch:rule [
993996
context = "tei:*[@subtype]"
994997
"\x{a}" ~
995-
" "
998+
" "
996999
sch:assert [
9971000
test = "@type"
9981001
"The "
@@ -1035,15 +1038,15 @@ sch:pattern [
10351038
sch:rule [
10361039
context = "tei:*[not(self::tei:schemaSpec)][@targetLang]"
10371040
"\x{a}" ~
1038-
" "
1041+
" "
10391042
sch:assert [
10401043
test = "@target"
10411044
"@targetLang should only be used on "
10421045
sch:name [ ]
10431046
" if @target is specified."
10441047
]
10451048
"\x{a}" ~
1046-
" "
1049+
" "
10471050
]
10481051
"\x{a}" ~
10491052
" "
@@ -1145,7 +1148,7 @@ sch:pattern [
11451148
sch:rule [
11461149
context = "tei:*[@spanTo]"
11471150
"\x{a}" ~
1148-
" "
1151+
" "
11491152
sch:assert [
11501153
test =
11511154
"id(substring(@spanTo,2)) and following::*[@xml:id=substring(current()/@spanTo,2)]"
@@ -1155,10 +1158,10 @@ sch:pattern [
11551158
") must follow the current element "
11561159
sch:name [ ]
11571160
"\x{a}" ~
1158-
" "
1161+
" "
11591162
]
11601163
"\x{a}" ~
1161-
" "
1164+
" "
11621165
]
11631166
"\x{a}" ~
11641167
" "
@@ -1202,15 +1205,15 @@ sch:pattern [
12021205
sch:rule [
12031206
context = "tei:*[@schemeVersion]"
12041207
"\x{a}" ~
1205-
" "
1208+
" "
12061209
sch:assert [
12071210
test = "@scheme and not(@scheme = 'free')"
12081211
"\x{a}" ~
12091212
" @schemeVersion can only be used if @scheme is specified.\x{a}" ~
12101213
" "
12111214
]
12121215
"\x{a}" ~
1213-
" "
1216+
" "
12141217
]
12151218
"\x{a}" ~
12161219
" "
@@ -1420,8 +1423,7 @@ tei_model.egLike_sequence = empty
14201423
tei_model.egLike_sequenceOptional = empty
14211424
tei_model.egLike_sequenceOptionalRepeatable = empty
14221425
tei_model.egLike_sequenceRepeatable = notAllowed
1423-
tei_model.graphicLike =
1424-
tei_media | tei_graphic | tei_binaryObject | tei_formula
1426+
tei_model.graphicLike = tei_media | tei_graphic | tei_formula
14251427
tei_model.offsetLike = tei_offset | tei_geogFeat
14261428
tei_model.offsetLike_alternation = tei_offset | tei_geogFeat
14271429
tei_model.offsetLike_sequence = tei_offset, tei_geogFeat
@@ -1431,17 +1433,17 @@ tei_model.offsetLike_sequenceOptionalRepeatable =
14311433
tei_model.offsetLike_sequenceRepeatable = tei_offset+, tei_geogFeat+
14321434
tei_model.pPart.msdesc = notAllowed
14331435
tei_model.pPart.editorial =
1434-
tei_choice | tei_abbr | tei_expan | tei_ex | tei_am | tei_subst
1436+
tei_choice | tei_abbr | tei_expan | tei_ex | tei_subst
14351437
tei_model.pPart.editorial_alternation =
1436-
tei_choice | tei_abbr | tei_expan | tei_ex | tei_am | tei_subst
1438+
tei_choice | tei_abbr | tei_expan | tei_ex | tei_subst
14371439
tei_model.pPart.editorial_sequence =
1438-
tei_choice, tei_abbr, tei_expan, tei_ex, tei_am, tei_subst
1440+
tei_choice, tei_abbr, tei_expan, tei_ex, tei_subst
14391441
tei_model.pPart.editorial_sequenceOptional =
1440-
tei_choice?, tei_abbr?, tei_expan?, tei_ex?, tei_am?, tei_subst?
1442+
tei_choice?, tei_abbr?, tei_expan?, tei_ex?, tei_subst?
14411443
tei_model.pPart.editorial_sequenceOptionalRepeatable =
1442-
tei_choice*, tei_abbr*, tei_expan*, tei_ex*, tei_am*, tei_subst*
1444+
tei_choice*, tei_abbr*, tei_expan*, tei_ex*, tei_subst*
14431445
tei_model.pPart.editorial_sequenceRepeatable =
1444-
tei_choice+, tei_abbr+, tei_expan+, tei_ex+, tei_am+, tei_subst+
1446+
tei_choice+, tei_abbr+, tei_expan+, tei_ex+, tei_subst+
14451447
tei_model.pPart.transcriptional =
14461448
tei_sic
14471449
| tei_corr
@@ -1938,7 +1940,6 @@ tei_model.divBottomPart =
19381940
tei_model.divBottom = tei_model.divWrapper | tei_model.divBottomPart
19391941
tei_model.titlepagePart =
19401942
tei_graphic
1941-
| tei_binaryObject
19421943
| tei_byline
19431944
| tei_docTitle
19441945
| tei_titlePart
@@ -1956,7 +1957,6 @@ tei_model.choicePart =
19561957
| tei_abbr
19571958
| tei_expan
19581959
| tei_ex
1959-
| tei_am
19601960
| tei_supplied
19611961
| tei_seg
19621962
tei_model.imprintPart =
@@ -2981,7 +2981,7 @@ tei_list =
29812981
sch:rule [
29822982
context = "tei:list[@type='gloss']"
29832983
"\x{a}" ~
2984-
" "
2984+
" "
29852985
sch:assert [
29862986
test = "tei:label"
29872987
'The content of a "gloss" list should include a sequence of one or more pairs of a label element followed by an item element'
@@ -3137,29 +3137,6 @@ tei_graphic =
31373137
tei_att.declaring.attributes,
31383138
empty
31393139
}
3140-
tei_binaryObject =
3141-
3142-
## provides encoded binary data representing an inline graphic, audio, video or other object. [3.9. Graphics and Other Non-textual Components]
3143-
element binaryObject {
3144-
text,
3145-
tei_att.global.attributes,
3146-
tei_att.media.attributes,
3147-
tei_att.timed.attributes,
3148-
tei_att.typed.attributes,
3149-
[
3150-
a:documentation [
3151-
"The encoding used to encode the binary data. If not specified, this is assumed to be "
3152-
ns1:a [ href = "http://en.wikipedia.org/wiki/Base64" "Base64" ]
3153-
"."
3154-
]
3155-
]
3156-
attribute encoding {
3157-
list {
3158-
xsd:token { pattern = "[^\p{C}\p{Z}]+" }+
3159-
}
3160-
}?,
3161-
empty
3162-
}
31633140
tei_milestone =
31643141

31653142
## marks a boundary point separating any kind of section of a text, typically but not necessarily indicating a point at which some part of a standard reference system changes, where the change is not represented by a structural element. [3.10.3. Milestone
@@ -5563,7 +5540,6 @@ tei_path =
55635540
sch:rule [
55645541
context = "tei:path[@points]"
55655542
"\x{a}" ~
5566-
" \x{a}" ~
55675543
" "
55685544
sch:let [
55695545
name = "firstPair"
@@ -5857,16 +5833,6 @@ tei_handShift =
58575833
attribute new { xsd:anyURI }?,
58585834
empty
58595835
}
5860-
tei_am =
5861-
5862-
## (abbreviation marker) contains a sequence of letters or signs present in an abbreviation which are omitted or replaced in the expanded form of the abbreviation. [11.3.1.2. Abbreviation and Expansion]
5863-
element am {
5864-
(text | tei_model.gLike | tei_model.pPart.transcriptional)*,
5865-
tei_att.global.attributes,
5866-
tei_att.typed.attributes,
5867-
tei_att.editLike.attributes,
5868-
empty
5869-
}
58705836
tei_restore =
58715837

58725838
## indicates restoration of text to an earlier state by cancellation of an editorial or authorial marking or instruction. [11.3.1.6. Cancellation of Deletions and Other Markings]
@@ -6190,11 +6156,7 @@ tei_notatedMusic =
61906156

61916157
## encodes the presence of music notation in a text [14.3. Notated Music in Written Text]
61926158
element notatedMusic {
6193-
(tei_model.labelLike
6194-
| tei_model.ptrLike
6195-
| tei_graphic
6196-
| tei_binaryObject
6197-
| tei_seg)*,
6159+
(tei_model.labelLike | tei_model.ptrLike | tei_graphic | tei_seg)*,
61986160
tei_att.global.attributes,
61996161
tei_att.placement.attributes,
62006162
tei_att.typed.attributes,

0 commit comments

Comments
 (0)