forked from freedict/fd-dictionaries
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathfreedict-P5.xml
280 lines (272 loc) · 17 KB
/
freedict-P5.xml
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
<?xml version="1.0" encoding="UTF-8"?>
<?oxygen RNGSchema="tei_odds.rng" type="xml"?>
<TEI
xmlns="http://www.tei-c.org/ns/1.0"
xmlns:sch="http://purl.oclc.org/dsdl/schematron"
xml:lang="en" n="freedict">
<teiHeader>
<fileDesc>
<titleStmt>
<title>TEI Customization for the FreeDict project (basic), version 0.10</title>
<respStmt>
<resp>maintained by</resp>
<name xml:id="bansp">Piotr Bański (bansp in the domain of o2.pl)</name>
</respStmt>
</titleStmt>
<publicationStmt>
<availability status="free">
<p>This file is released as part of the FreeDict package (http://freedict.org/). It
is licensed under the GNU Public License version 2.0 or later.</p>
</availability>
</publicationStmt>
<sourceDesc>
<p>Initial version created with Roma, the ODD generator, version 3.6.</p>
<p>This file was initially used for the Swahili-English dictionary. Later on, it got
generalised as the basic schema for Freedict dictionaries encoded in TEI P5.</p>
</sourceDesc>
</fileDesc>
</teiHeader>
<text>
<body>
<head>ODD for FreeDict dictionaries, basic level of conformance.</head>
<p>This is the ODD driver for generating schemas and documentation for dictionaries in the
FreeDict project (see http://freedict.org/). It is meant primarily for dictionaries with
very basic structure, but until higher-level ODDs are created, it will serve all TEI P5
dictionaries. For details, see a TEI Conference and Members' Meeting presentation by
Piotr Bański and Beata Wójtowicz, which should be available from
http://www.lib.umich.edu/spo/teimeeting09/program.html.</p>
<list n="changelog" type="glossed">
<item><label>Version 0.10, <date when="2011-09-09">9 September 2011</date>, by <name>Piotr
Bański</name></label>: Added the <gi>cell</gi>, <gi>row</gi>, and <gi>table</gi> elements,
to handle front matter better.</item>
<item><label>Version 0.9, <date when="2010-11-08">8 November 2010</date>, by <name>Piotr
Bański</name></label>:
<list type="bulleted">
<item>Added further Schematron constraints on the contents of <gi>tagUsage</gi>:
when the <att>rend</att> on an ancestor is set to <val>anchored</val>, the
<att>ana</att> attributes are traced to the FreeDict ontology interface (off
by default, because it needs a checkout of the shared/ directory. See kha-deu
for an example in action.</item>
<item>Commented out the 'figures' module, until it is ever? needed.</item>
<item>Removed <gi>tagUsage</gi> from the att.typed class added earlier in v. 0.8,
because I decided to forcefully abuse the elements and attributes involved
(mostly <gi>namespace</gi>, <att>n</att> and <att>rend</att>).</item>
<item>TODO: extend this system for <gi>subcat</gi> elements.</item>
</list>
</item>
<item><label>Version 0.8, <date when="2010-11-06">6 November 2010</date>, by <name>Piotr
Bański</name></label>:
<list type="bulleted">
<item>Added Schematron constraints on <gi>tagUsage</gi> (so this may be the
beginning of the end of DTDs for Freedict, and consequently the xinclude
extension will be able to go);</item>
<item>added <gi>tagUsage</gi> to the att.typed class (need to distinguish between
tags used in the <gi>gramGroup</gi> describing the source language forms from
those describing the target language (inside <gi>cit</gi>);</item>
<item>added <gi>gramGrp</gi> to the att.typed class (in order to be able to talk
about 'discharged' grammatical properties, in elements that trigger agreement
on other elements (think noun classes));</item>
<item>Took out module "iso-fs" - I think it was here while I still thought of
ontology interfaces being plugged more directly into dictionaries, not via
tagUsage (or maybe I'm forgetting something now...).</item>
</list>
</item>
<item><label>Version 0.7, <date when="2010-04-25">25 April 2010</date>, by <name>Piotr
Bański</name></label>: Added the xinclude extension from the approoriate Roma
template, changed it to be able to occur as a child of front (I can't validate
xinclusions with xmllint if a DTD is used, so this is for the sake of DTDs
only)</item>
<item><label>Version 0.6, <date when="2010-04-24">24 April 2010</date>, by <name>Piotr Bański</name></label>: Added the "iso-fs" and "analysis" modules, the latter for the sake of @ana only...</item>
<item><label>Version 0.5, <date when="2010-04-16">16 April 2010</date>, edited by <name>Piotr Bański</name></label>
<list type="bulleted">
<item>Changed the responsibility type from the Roma-generated <gi>author</gi> to <gi>respStmt</gi> and called myself a maintainer.</item>
<item>Made the changelog dates machine-readable.</item>
<item>Added the linking module (merged changes by <name>Stuart Yeates</name>). This is to enable the <att>corresp</att> attributes.</item>
</list>
</item>
<item><label>Version 0.4, <date when="2009-12-31">31 December 2009</date> by <name>Piotr Bański</name></label>
<list type="bulleted">
<item>Commited to the Freedict CVS (still in version 0.3).</item>
<item>Properly re-titled and described.</item>
<item>Added the "figures" module, for tables in the front matter.</item>
</list>
</item>
<item><label>Version 0.3, <date when="2008-12-30">30 December 2008</date> by <name>Piotr Bański</name></label>
<list type="bulleted">
<item>Removed <gi>dictScrap</gi> and <gi>entryFree</gi> and the mysterious header
elements that cause Sanity Checker warnings.</item>
<item>Removed numbered divs (with a view towards tailoring this ODD for all
FreeDict dictionaries).</item>
</list>
</item>
</list>
<schemaSpec ident="freedict-P5" docLang="en" prefix="tei_">
<moduleRef key="core"/>
<elementSpec module="core" ident="teiCorpus" mode="delete"/>
<moduleRef key="tei"/>
<moduleRef key="header"/>
<elementSpec module="header" ident="handNote" mode="delete"/>
<elementSpec module="header" ident="typeNote" mode="delete"/>
<elementSpec module="header" ident="tagUsage" mode="change">
<!-- <classes mode="replace">
<memberOf key="att.typed" mode="add"/>
</classes>
--> <constraintSpec ident="tagUsage_stuff" scheme="isoschematron">
<desc>Make sure that the content of gramGrp (of various sorts) corresponds to
whatever is defined in tagUsage *if* it is defined there.</desc>
<constraint>
<sch:pattern id="gramGrp-tagUsage_conformance">
<sch:rule
context="/tei:TEI/tei:text/tei:body//tei:*[local-name() eq 'entry' or local-name() eq 'sense']/tei:gramGrp/tei:*">
<sch:let name="loc_name" value="local-name()"/>
<sch:assert
test="not(/tei:TEI/tei:teiHeader/tei:encodingDesc/tei:tagsDecl/tei:namespace[@name eq 'http://www.tei-c.org/ns/1.0']/tei:tagUsage[@gi eq $loc_name]/tei:list/tei:item) or (. = /tei:TEI/tei:teiHeader/tei:encodingDesc/tei:tagsDecl/tei:namespace[@name eq 'http://www.tei-c.org/ns/1.0']/tei:tagUsage[@gi eq $loc_name]/tei:list/tei:item)"
>The values of gramGrp/<sch:name/> must belong to the set identified
in tagUsage for this element.</sch:assert>
</sch:rule>
<sch:rule
context="/tei:TEI/tei:text/tei:body//tei:cit[@type eq 'trans']/tei:gramGrp/tei:*">
<!-- big question: is the context here stated properly? is it not too narrow now? -->
<sch:let name="loc_name" value="local-name()"/>
<sch:assert
test="not(/tei:TEI/tei:teiHeader/tei:encodingDesc/tei:tagsDecl/tei:namespace[@name eq 'http://www.tei-c.org/ns/1.0'][@n eq 'equiv']/tei:tagUsage[@gi eq $loc_name]/tei:list/tei:item) or (. = /tei:TEI/tei:teiHeader/tei:encodingDesc/tei:tagsDecl/tei:namespace[@name eq 'http://www.tei-c.org/ns/1.0'][@n eq 'equiv']/tei:tagUsage[@gi eq $loc_name]/tei:list/tei:item)"
>The values of cit[@type='trans']/gramGrp/<sch:name/> must belong to the set identified in
tagUsage for this element, in the 'equiv' section.</sch:assert>
</sch:rule>
<sch:rule
context="/tei:TEI/tei:text/tei:body//tei:*[local-name() eq 'entry' or local-name() eq 'sense']/tei:gramGrp/tei:gramGrp[@type='agr']/tei:*">
<sch:let name="loc_name" value="local-name()"/>
<sch:assert
test="not(/tei:TEI/tei:teiHeader/tei:encodingDesc/tei:tagsDecl/tei:namespace[@name eq 'http://www.tei-c.org/ns/1.0'][@n eq 'agr']/tei:tagUsage[@gi eq $loc_name]/tei:list/tei:item) or (. = /tei:TEI/tei:teiHeader/tei:encodingDesc/tei:tagsDecl/tei:namespace[@name eq 'http://www.tei-c.org/ns/1.0'][@n eq 'agr']/tei:tagUsage[@gi eq $loc_name]/tei:list/tei:item)"
>The values of gramGrp[@type='agr']/<sch:name/> must belong to the set identified in
tagUsage for this element, in the 'agr' section.</sch:assert>
</sch:rule>
</sch:pattern>
</constraint>
</constraintSpec>
<constraintSpec ident="tagUsage-item-external" scheme="isoschematron">
<desc>if this is an anchored description, for each item check if it identifies a resource in the FreeDict ontology interface</desc>
<constraint>
<sch:pattern id="tagUsage_item_check">
<sch:rule context="tei:list/tei:item">
<sch:let name="targ_res" value="document(@ana)"/>
<sch:assert test="if(ancestor::tei:tagsDecl[@rend eq 'anchored'] or ancestor::tei:namespace[@rend eq 'anchored'] or ancestor::tei:tagUsage[@rend eq 'anchored']) then (exists($targ_res) and string-length($targ_res)) else true()">The @ana attributes should identify a resource fragment in the FreeDict ontology interface.</sch:assert>
</sch:rule>
</sch:pattern>
</constraint>
</constraintSpec>
</elementSpec>
<moduleRef key="textstructure"/>
<elementSpec module="textstructure" ident="div1" mode="delete"/>
<elementSpec module="textstructure" ident="div2" mode="delete"/>
<elementSpec module="textstructure" ident="div3" mode="delete"/>
<elementSpec module="textstructure" ident="div4" mode="delete"/>
<elementSpec module="textstructure" ident="div5" mode="delete"/>
<elementSpec module="textstructure" ident="div6" mode="delete"/>
<elementSpec module="textstructure" ident="div7" mode="delete"/>
<moduleRef key="dictionaries"/>
<elementSpec module="dictionaries" ident="dictScrap" mode="delete"/>
<elementSpec module="dictionaries" ident="entryFree" mode="delete"/>
<elementSpec ident="gramGrp" module="dictionaries" mode="change">
<classes mode="replace">
<memberOf key="model.entryPart"/>
<memberOf key="model.entryPart.top"/>
<memberOf key="model.gramPart"/>
<memberOf key="att.lexicographic"/>
<memberOf key="att.typed" mode="add"/>
</classes>
</elementSpec>
<moduleRef key="figures" include="cell row table"/>
<moduleRef key="analysis"/>
<elementSpec module="analysis" ident="c" mode="delete"/>
<elementSpec module="analysis" ident="cl" mode="delete"/>
<elementSpec module="analysis" ident="interp" mode="delete"/>
<elementSpec module="analysis" ident="interpGrp" mode="delete"/>
<elementSpec module="analysis" ident="m" mode="delete"/>
<elementSpec module="analysis" ident="pc" mode="delete"/>
<elementSpec module="analysis" ident="phr" mode="delete"/>
<elementSpec module="analysis" ident="s" mode="delete"/>
<elementSpec module="analysis" ident="span" mode="delete"/>
<elementSpec module="analysis" ident="spanGrp" mode="delete"/>
<elementSpec module="analysis" ident="w" mode="delete"/>
<moduleRef key="linking"/>
<elementSpec module="linking" ident="ab" mode="delete"/>
<elementSpec module="linking" ident="alt" mode="delete"/>
<elementSpec module="linking" ident="altGrp" mode="delete"/>
<elementSpec module="linking" ident="anchor" mode="delete"/>
<elementSpec module="linking" ident="join" mode="delete"/>
<elementSpec module="linking" ident="joinGrp" mode="delete"/>
<elementSpec module="linking" ident="link" mode="delete"/>
<elementSpec module="linking" ident="linkGrp" mode="delete"/>
<elementSpec module="linking" ident="seg" mode="delete"/>
<elementSpec module="linking" ident="timeline" mode="delete"/>
<elementSpec module="linking" ident="when" mode="delete"/>
<classSpec ident="att.global.linking" mode="change" type="atts" module="linking">
<attList>
<attDef ident="synch" mode="delete"/>
<attDef ident="sameAs" mode="delete"/>
<attDef ident="copyOf" mode="delete"/>
<attDef ident="next" mode="delete"/>
<attDef ident="prev" mode="delete"/>
<attDef ident="exclude" mode="delete"/>
<attDef ident="select" mode="delete"/>
</attList>
</classSpec>
<elementSpec xmlns:rng="http://relaxng.org/ns/structure/1.0" ident="include"
ns="http://www.w3.org/2001/XInclude" mode="add">
<desc>The W3C XInclude element</desc>
<classes>
<!--<memberOf key="model.common"/>-->
<memberOf key="model.pLike.front"/>
<memberOf key="model.headerPart"/>
</classes>
<content>
<rng:optional>
<rng:ref name="fallback"/>
</rng:optional>
</content>
<attList>
<attDef ident="href">
<desc>pointer to the resource being included</desc>
<datatype>
<rng:ref name="data.pointer"/>
</datatype>
</attDef>
<attDef ident="parse" usage="opt">
<defaultVal>xml</defaultVal>
<valList type="closed">
<valItem ident="xml"/>
<valItem ident="text"/>
</valList>
</attDef>
<attDef ident="xpointer" usage="opt">
<datatype>
<rng:text/>
</datatype>
</attDef>
<attDef ident="encoding" usage="opt">
<datatype>
<rng:text/>
</datatype>
</attDef>
<attDef ident="accept" usage="opt">
<datatype>
<rng:text/>
</datatype>
</attDef>
<attDef ident="accept-charset" usage="opt">
<datatype>
<rng:text/>
</datatype>
</attDef>
<attDef ident="accept-language" usage="opt">
<datatype>
<rng:text/>
</datatype>
</attDef>
</attList>
</elementSpec>
</schemaSpec>
</body>
</text>
</TEI>