From c0f2d29807fcae9c1a48249cab35620cd6c26a07 Mon Sep 17 00:00:00 2001 From: Adam Radziszewski <adam.radziszewski@pwr.wroc.pl> Date: Fri, 26 Oct 2012 09:15:23 +0200 Subject: [PATCH] add XCES DTDs --- doc/xcesAnaIPI.dtd | 241 +++++++++++++++++++ doc/xheaderIPI.elt | 574 +++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 815 insertions(+) create mode 100644 doc/xcesAnaIPI.dtd create mode 100644 doc/xheaderIPI.elt diff --git a/doc/xcesAnaIPI.dtd b/doc/xcesAnaIPI.dtd new file mode 100644 index 0000000..ea88b43 --- /dev/null +++ b/doc/xcesAnaIPI.dtd @@ -0,0 +1,241 @@ +<!-- --> +<!-- --> +<!-- Corpus Encoding Standard --> +<!-- --> +<!-- CES --> +<!-- --> +<!-- Encoding conventions for annotated data --> +<!-- --> +<!-- --> +<!-- Modified for the IPI PAN corpus --> +<!-- Version IPI-1.6 --> +<!-- --> +<!-- --> +<!-- --> +<!-- --> +<!-- --> +<!-- + Original Date: 1996/08/05 19:07:30 + Original Revision: 1.11 + Author of 1.11: Patrice Bonhomme + + $Id: xcesAnaIPI.dtd,v 1.1.1.1 2007/11/08 15:26:49 adamp Exp $ +* $Log: xcesAnaIPI.dtd,v $ +* Revision 1.1.1.1 2007/11/08 15:26:49 adamp +* Spejd +* +* Revision 1.1 2007/10/20 13:11:39 adamp +* *** empty log message *** +* +* Revision 1.6 2006/06/03 12:53:28 adamp +* Updated version number of xcesAnaIPI.dtd. +* +* Revision 1.5 2006/06/03 12:45:41 adamp +* Simplified. +* +* Revision 1.2 2006/06/03 12:33:13 adamp +* Changed name from doc2ana.sh to index.morph.sh. +* +* Revision 1.1 2006/06/03 11:43:59 adamp +* *** empty log message *** +* +* Revision 1.4 2006/02/03 14:00:50 adamp +* Corresponding change of version number (to 1.3). +* +* Revision 1.3 2006/02/03 13:59:03 adamp +* Changed (tok|ns)+ to (tok|ns)* - let's hope that Poliqarp can deal with empty chunks... +* +* Revision 1.2 2004-03-16 19:00:48 adamp +* ATTLIST for lex was defined twice, so I've removed the first +* definition. This caused version change to IPI-1.2 (maybe it shouldn't +* have, but just to be on the safe side). +* +* Revision 1.1.1.1 2004/03/10 19:21:29 adamp +* x2XCES converters for the IPI PAN corpus +* +* Revision 1.14 2004/03/01 16:00:48 adamp +* New version: 'IPI-1.1'. +* +* Revision 1.13 2004/03/01 15:58:05 adamp +* Only typos in comments. +* +* Revision 1.12 2004/03/01 13:58:55 adamp +* PB's modifications: the value of 'lang' is CDATA now, and the locus of +* xmlns:xlink changed. +* +* Revision 1.11 2004/03/01 10:55:46 adamp +* PB's modifications. +* +* Revision 1.11 2004/03/01 01:15:30 piotr +* Added fully specified xmlns:xlink (to make the xlink namespace legal) +* and the xml:base attribute for use in <chunkList> +* +* $Log: xcesAnaIPI.dtd,v $ +* Revision 1.1.1.1 2007/11/08 15:26:49 adamp +* Spejd +* +* Revision 1.1 2007/10/20 13:11:39 adamp +* *** empty log message *** +* +* Revision 1.6 2006/06/03 12:53:28 adamp +* Updated version number of xcesAnaIPI.dtd. +* +* Revision 1.5 2006/06/03 12:45:41 adamp +* Simplified. +* +* Revision 1.2 2006/06/03 12:33:13 adamp +* Changed name from doc2ana.sh to index.morph.sh. +* +* Revision 1.1 2006/06/03 11:43:59 adamp +* *** empty log message *** +* +* Revision 1.4 2006/02/03 14:00:50 adamp +* Corresponding change of version number (to 1.3). +* +* Revision 1.3 2006/02/03 13:59:03 adamp +* Changed (tok|ns)+ to (tok|ns)* - let's hope that Poliqarp can deal with empty chunks... +* +* Revision 1.2 2004-03-16 19:00:48 adamp +* ATTLIST for lex was defined twice, so I've removed the first +* definition. This caused version change to IPI-1.2 (maybe it shouldn't +* have, but just to be on the safe side). +* +* Revision 1.1.1.1 2004/03/10 19:21:29 adamp +* x2XCES converters for the IPI PAN corpus +* +* Revision 1.14 2004/03/01 16:00:48 adamp +* New version: 'IPI-1.1'. +* +* Revision 1.13 2004/03/01 15:58:05 adamp +* Only typos in comments. +* +* Revision 1.12 2004/03/01 13:58:55 adamp +* PB's modifications: the value of 'lang' is CDATA now, and the locus of +* xmlns:xlink changed. +* +* Revision 1.11 2004/03/01 10:55:46 adamp +* PB's modifications. +* +* Revision 1.10 2004/02/27 22:38:09 adamp +* Wyrzucone atrybuty xml..., dodany element <ns> (no space). +* +* Revision 1.9 2004/02/25 23:00:34 adamp +* Changes in comments only. +* +* Revision 1.8 2004/02/25 16:36:50 adamp +* Re-introducing various modifications by PB. +* +* Revision 1.7 2004/02/22 19:10:58 adamp +* Only minor changes in comments. +* +* Revision 1.6 2004/02/12 15:43:47 adamp +* *** empty log message *** +* +* Revision 1.5 2004/02/11 22:38:47 adamp +* Typo. +* +* Revision 1.4 2004/02/10 17:51:51 adamp +* Wersja zawierająca <par> (tak jak w oryginalnym XCES, inaczej niż w +* wersji Piotrka Bańskiego). +* +* Revision 1.3 2004/02/10 17:18:09 adamp +* No real change, just testing CVS. +* +* Revision 1.2 2004/02/10 17:17:30 adamp +* Added xmlns. + + This is a modification of the original CES DTD designed for use with + the IPI PAN Corpus. Created by Adam Przepiórkowski, on the basis of + ealier modifications by Piotr Bański, cf. PB (who's the author of + the vast majority of changes, as of 9th February 2004). + + --> + +<!-- Global attributes --> + +<!-- Modification by Piotr Bański: --> +<!-- The addition of the xlink:href attribute below. --> +<!-- PB, 010304: 'lang IDREFS' zmienione na 'lang CDATA'. --> +<!ENTITY % a.global ' + id ID #IMPLIED + n CDATA #IMPLIED + xml:lang CDATA #IMPLIED + xlink:href CDATA #IMPLIED + lang CDATA #IMPLIED' > + +<!-- Modification by PB: adding xlink:... attributes. Also xml:base. --> +<!ENTITY % a.ana '%a.global; + xml:base CDATA #IMPLIED + type CDATA #IMPLIED + wsd CDATA #IMPLIED' > + + +<!ELEMENT cesAna (cesHeader?, chunkList) > +<!-- Modification by PB: xmlns:xlink. --> +<!ATTLIST cesAna %a.ana; + doc CDATA #IMPLIED + xmlns:xlink CDATA "http://www.w3.org/1999/xlink" + version CDATA #REQUIRED > + +<!ENTITY % xces.header SYSTEM 'xheaderIPI.elt' > +%xces.header; + +<!ELEMENT chunkList (chunk)+ > +<!ATTLIST chunkList %a.ana; > + +<!-- AP: Chunks contain either smaller chunks or tokens + no white space --> +<!-- markers. --> +<!-- AP: Changed + to * - let's hope that Poliqarp can deal with empty chunks... --> +<!ELEMENT chunk ((tok|ns)* | chunk+) > +<!-- PB's modification: no attributes 'doc', 'from' and 'to'. --> +<!ATTLIST chunk %a.ana; > + +<!-- AP: elements 'par' and 's' disappear; instead, there chunks of type --> +<!-- 's' and 'p'. --> + + +<!-- PB's modification (and comment) --> +<!-- +threw out the disamb element - it will be an attribute now +more simplification: +eliminated msds, cause we use ctags for them; guarantee at least one lex; +--> +<!ELEMENT tok (orth, lex+) > + +<!-- PB's modification: --> +<!-- Removed attributes 'from' and 'to'. --> +<!ATTLIST tok %a.ana; + class CDATA #IMPLIED > + +<!-- AP: Adding a 'no white space between tokens' marker: --> +<!ELEMENT ns EMPTY > + +<!ELEMENT orth (#PCDATA) > +<!ATTLIST orth %a.ana; > + +<!-- PB's modification (and comment): --> +<!-- +msd removed for simplicity, we use msds as ctags +and ctags are grouped around a unique base (note: uniqueness of the base is not +guaranteed by the DTD) +--> +<!ELEMENT lex (base, ctag+) > +<!-- AP: gotten rid of spurious attlist for lex. --> +<!-- <!ATTLIST lex %a.ana; > --> + + +<!-- Modification by Piotr Bański: --> +<!-- duplicated 'disamb' with 'human', indicating hand-checked bits --> +<!ATTLIST lex %a.ana; + disamb (1 | 0) #IMPLIED + human (1 | 0) #IMPLIED > + +<!ELEMENT base (#PCDATA) > +<!ATTLIST base %a.ana; > + +<!-- The msd element removed (by PB). --> + +<!-- PB's modification and comment: --> +<!-- added the disamb attribute here --> +<!ELEMENT ctag (#PCDATA) > +<!ATTLIST ctag %a.ana; > diff --git a/doc/xheaderIPI.elt b/doc/xheaderIPI.elt new file mode 100644 index 0000000..7ea1600 --- /dev/null +++ b/doc/xheaderIPI.elt @@ -0,0 +1,574 @@ +<!-- --> +<!-- THE CES HEADER --> +<!-- --> +<!-- This is the entity ces.header used in the --> +<!-- Corpus Encoding Standard DTDs. --> +<!-- --> +<!-- It is referred to in those DTDs as xheaderIPI.elt. --> +<!-- --> +<!-- --> +<!-- + Original Date: 1996/04/09 02:33:47 + Original Revision: 2.1 + Author of 2.1: Patrice Bonhomme + + Current Revision id: 2.1.IPI.16 + + Modified for the second edition of the IPI PAN Corpus by Rafał + Górski. + + Modified for the IPI PAN Corpus by Adam Przepiórkowski, + partially on the basis of earlier modifications by Piotr + Bański, cf. PB. + + It differs from the standard CES as described in version 1.5 of + Corpus Encoding Standard, http://www.cs.vassar.edu/CES/, in the + following ways: + - addition of xcesHeader (PB), + - origDate added to imprint (AP), + - as well as to analytic (AP), + - various subsequent changes by RG. + + Also, the followin recommendations override the recommendations + of the version 1.5 of CES: + - names should be given as they occur on the title page (cf. the + example at the end of section 3), and not "in a canonical + form, with surnames preceding forenames" (cf. section 3.3.5 of + CES); + - the 'vol' value of the 'type' attribute of biblScope + represents the continuous number of a periodical publication, + e.g., volume of a journal or the year of publication of a + newspaper, while 'issue' represents the cyclic number, e.g., + the month number of a monthly, or the number of the issue of a + newspaper within a give year; + - UTF-8 should be used instead of ISO-8859-X; + - the values of the attribute 'value' of various Date elements + (pubDate, createDate, etc.) should adhere to the smallest + subset of the ISO 8061 standard corresponding to the following + examples: + - '19' = 20th century + - '1985' = the year 1985 + - '1985-12' = December 1985 + - '1985-12-24' = 24th December 1985 + Values involving local (Warsaw) time: + - '1985-12-24T10' = 10m on 24th December 1985 + - '1985-12-24T14' = 2pm on 24th December 1985 + - '1985-12-24T14:15' = 2:15pm on 24th December 1985 + - '1985-12-24T14:15:30' = 15 minutes and 30 seconds after 2pm + on 24th December 1985 + + $Id: xheaderIPI.elt,v 1.1.1.1 2007/11/08 15:26:49 adamp Exp $ +* $Log: xheaderIPI.elt,v $ +* Revision 1.1.1.1 2007/11/08 15:26:49 adamp +* Spejd +* +* Revision 1.1 2007/10/20 13:11:39 adamp +* *** empty log message *** +* +* Revision 1.16 2006/05/14 12:36:02 adamp +* A comment problem again. +* +* Revision 1.15 2006/05/14 11:38:58 adamp +* No changes apart from the correction of log for Revision 1.14. +* +* Revision 1.14 2006/05/14 11:36:34 adamp +* Wyrzucenie nieistniejacych odwolan do "extent" i "editionStmt" - +* zauwazone przez Wojciecha Rygielskiego, informacja przekazana przez +* Aleksandra Buczynskiego. +* +* Revision 1.13 2006/03/13 19:45:59 adamp +* *** empty log message *** +* +* Revision 1.12 2005/11/23 16:00:29 adamp +* Minor syntactic problem (result of merge) corrected; the previous +* version was ill-formed. +* +* Revision 1.11 2005/11/23 15:57:15 adamp +* Optional <domain> added. Revision number changed to 2.1.IPI.12. +* +* Revision 1.10 2005/11/02 13:47:57 adamp +* Added respStmt and definitions of elements within respStmt. +* +* Revision 1.9 2005/11/02 13:42:57 adamp +* Added respStmt; should be used only in sourceDesc (as in +* SienkiewiczH-qv, etc.), not in fileDesc. +* +* Revision 1.8 2005/11/02 11:59:31 adamp +* Added idno to monogr; version number changed to ...10. +* +* Revision 1.7 2005/11/02 09:59:03 adamp +* *** empty log message *** +* +* Revision 1.6 2005/09/27 10:36:46 adamp +* Zmiana wersji na 2.1.IPI.8. +* +* Revision 1.5 2005/09/26 21:28:05 adamp +* *** empty log message *** +* +* Revision 1.4 2005/09/26 10:30:10 adamp +* Druga propozycja xheaderaIPI.elt od RG +* +* Revision 1.3 2005/09/26 10:28:15 adamp +* Druga propozycja xheaderaIPI.elt od RG +* +* Revision 1.2 2005/09/26 09:56:53 adamp +* Druga propozycja xheaderaIPI.elt od RG. +* +* Revision 1.3 2004/04/23 14:20:51 adamp +* Analytic now has its own origDate (optionally, of course). This +* should not change the validity of previous header.xmls. +* +* Revision 1.2 2004/03/28 23:47:00 adamp +* Elements createDate and firstPubDate need the 'value' attribute! +* +* Revision 1.1.1.1 2004/03/10 19:21:29 adamp +* x2XCES converters for the IPI PAN corpus +* +* Revision 1.12 2004/03/01 15:59:14 adamp +* New version: 2.1.IPI.5. +* +* Revision 1.11 2004/03/01 15:58:05 adamp +* Only typos in comments. +* +* Revision 1.10 2004/02/25 16:38:22 adamp +* Changes in comments only. +* +* Revision 1.9 2004/02/25 16:16:20 adamp +* Only comments changed. +* +* Revision 1.8 2004/02/22 18:39:30 adamp +* Only minor changes in comments. +* +* Revision 1.7 2004/02/12 15:52:06 adamp +* The attribute 'Default' changed to 'default'. +* +* Revision 1.6 2004/02/12 15:43:47 adamp +* *** empty log message *** +* +* Revision 1.5 2004/02/12 14:53:44 adamp +* *** empty log message *** +* +* Revision 1.4 2004/02/11 20:04:48 adamp +* Added origDate, revision number and comments. +* +* Revision 1.3 2004/02/11 17:55:33 adamp +* Log added. +* + --> +<!ENTITY % a.header '%a.global;' > + +<!-- PB's modification: --> +<!-- Changed Default to default. --> +<!ENTITY % a.declarable ' + default (y | n) "n" ' > + + + +<!-- wszystki elementy obowiązkowe rg--> + +<!ELEMENT cesHeader (fileDesc, encodingDesc, + profileDesc, revisionDesc) > +<!ATTLIST cesHeader %a.header; + type CDATA "text" + creator CDATA #IMPLIED + status (new | update) "new" + date.created CDATA #IMPLIED + date.updated CDATA #IMPLIED + version CDATA #REQUIRED + TEIform CDATA "teiHeader" > + +<!-- PB's modification: --> +<!-- Kludged xcesHeader into here. Made it EMPTY, too. --> + +<!ELEMENT xcesHeader EMPTY > +<!ATTLIST xcesHeader xlink:href CDATA #REQUIRED > + +<!-- File Description --> +<!-- editionStmt i extent usunięte --> + +<!ELEMENT fileDesc (titleStmt, + publicationStmt, sourceDesc+ ) > +<!ATTLIST fileDesc %a.header; > + +<!ELEMENT titleStmt (h.title, respStmt*) > +<!ATTLIST titleStmt %a.header; > + +<!ELEMENT h.title ( #PCDATA ) > +<!ATTLIST h.title %a.header; > + +<!ELEMENT respStmt (respType | respName)+ > +<!ATTLIST respStmt %a.header; > + +<!ELEMENT respType (#PCDATA) > +<!ATTLIST respType %a.header; > + +<!ELEMENT respName (#PCDATA) > +<!ATTLIST respName %a.header; > + + +<!-- Edition Statement --> +<!-- wylatuje --> + + +<!-- Extent statement --> +<!-- wylatuje --> + + + + +<!-- Publication statement --> +<!-- nie zmieniałem elementów opcjonalnych na obligatoryjne, niezależnie od tego, że takimi są w headerach do Adama--> + +<!ELEMENT publicationStmt + (distributor, pubAddress, + telephone*, fax*, + eAddress*, idno*, + availability, pubDate ) > +<!ATTLIST publicationStmt %a.header; > + +<!ELEMENT distributor (#PCDATA) > +<!ATTLIST distributor %a.header; > + + +<!ELEMENT pubAddress (#PCDATA) > +<!ATTLIST pubAddress %a.header; > + +<!ELEMENT telephone (#PCDATA) > +<!ATTLIST telephone %a.header; > + +<!ELEMENT fax (#PCDATA) > +<!ATTLIST fax %a.header; > + + +<!ELEMENT eAddress (#PCDATA) > +<!ATTLIST eAddress %a.header; + type CDATA "email" > + +<!ELEMENT idno (#PCDATA) > +<!ATTLIST idno %a.header; + type CDATA "ISBN" > + +<!ELEMENT availability (#PCDATA ) > +<!ATTLIST availability %a.header; + region CDATA "world" + status (free | unknown | restricted) + "unknown" > + +<!ELEMENT pubDate (#PCDATA ) > +<!ATTLIST pubDate %a.header; + value CDATA #IMPLIED > + +<!-- Added origDate: the date of creation and/or first publication --> +<!-- of the work (AP). --> + +<!ELEMENT origDate ((createDate|firstPubDate)+) > +<!ATTLIST origDate %a.header; > + +<!ELEMENT createDate (#PCDATA ) > +<!ATTLIST createDate %a.header; + value CDATA #REQUIRED > + +<!ELEMENT firstPubDate (#PCDATA ) > +<!ATTLIST firstPubDate %a.header; + value CDATA #REQUIRED > + +<!-- Source description --> + +<!ELEMENT sourceDesc (biblFull | biblStruct) > +<!ATTLIST sourceDesc %a.header; + %a.declarable; > + +<!-- Bibliographic citation for non-electronic source --> + +<!ELEMENT biblStruct (analytic?, monogr+) > +<!ATTLIST biblStruct %a.header; + %a.declarable; > + +<!ELEMENT analytic (h.author | respStmt | + h.title | origDate)* > +<!ATTLIST analytic %a.header; > + +<!-- AP: Added idno, as in the original header.elt. --> +<!ELEMENT monogr (h.title+, + (h.author | respStmt)*, + (edition, respStmt?)*, imprint+, + idno*, + (biblNote | biblScope)* ) > +<!ATTLIST monogr %a.header; > + +<!ELEMENT h.author (#PCDATA) > +<!ATTLIST h.author %a.header; > + +<!ELEMENT edition (#PCDATA ) > +<!ATTLIST edition %a.header; > + +<!-- Added origDate the date of creation and/or first publication --> +<!-- of the work (AP). --> + +<!ELEMENT imprint (pubPlace | publisher | pubDate | origDate)* > +<!ATTLIST imprint %a.header; > + +<!ELEMENT pubPlace (#PCDATA) > +<!ATTLIST pubPlace %a.header; > + +<!ELEMENT publisher (#PCDATA) > +<!ATTLIST publisher %a.header; + type (place | org | person) + #IMPLIED > + +<!ELEMENT biblScope (#PCDATA) > +<!ATTLIST biblScope %a.header; + type (pp | vol | issue) #IMPLIED > + +<!ELEMENT biblNote (#PCDATA) > +<!ATTLIST biblNote %a.header; > + + +<!-- Bibliographical info for source in electronic form --> + +<!ELEMENT biblFull (titleStmt, + publicationStmt, + sourceDesc+ ) > +<!ATTLIST biblFull %a.header; > + + +<!-- Encoding description --> +<!-- samplingDecl usunięte, bo "This element is relevant only in the corpus header" http://www.cs.vassar.edu/CES/CES1-3.html#ToCsamp --> + + +<!-- tagsDecl, refsDecl, classDecl: usunięte --> + + + +<!ELEMENT encodingDesc (projectDesc, + editorialDecl*) > +<!ATTLIST encodingDesc %a.header; > + +<!ELEMENT projectDesc (#PCDATA) > +<!ATTLIST projectDesc %a.header; + %a.declarable; > + +<!-- wylatuje --> +<!-- +<!ELEMENT samplingDecl (#PCDATA) > +<!ATTLIST samplingDecl %a.header; + %a.declarable; > +--> + +<!-- Editorial declaration --> + +<!ELEMENT editorialDecl (correction | quotation + | hyphenation | segmentation | + transduction | normalization | + conformance)+ > +<!ATTLIST editorialDecl %a.header; + %a.declarable; > + +<!ELEMENT correction (#PCDATA) > +<!ATTLIST correction %a.header; + %a.declarable; + status (high | medium | low | unknown) + "unknown" + method (silent | tags) "silent" > + +<!ELEMENT quotation (#PCDATA) > +<!ATTLIST quotation %a.header; + %a.declarable; + marks (none | some | all) "all" + form (data | rend | std | + nonstd | unknown) "unknown" > + +<!ELEMENT hyphenation (#PCDATA) > +<!ATTLIST hyphenation %a.header; + %a.declarable; > + +<!ELEMENT segmentation (#PCDATA) > +<!ATTLIST segmentation %a.header; + %a.declarable; > + +<!ELEMENT transduction (#PCDATA) > +<!ATTLIST transduction %a.header; + %a.declarable; > + +<!ELEMENT normalization (#PCDATA) > +<!ATTLIST normalization %a.header; + %a.declarable; + source CDATA #IMPLIED + method (silent | tags) "silent" > + +<!ELEMENT conformance (#PCDATA) > +<!ATTLIST conformance %a.header; + level (0 | 1 | 2 | 3) "1" > + + +<!-- odtąd wylatują elementy usunięte z definicji encodingDesc + + Tag declaration + +<!ELEMENT tagsDecl (tagUsage+) > +<!ATTLIST tagsDecl %a.header; + +> + +<!ELEMENT tagUsage (#PCDATA) > +<!ATTLIST tagUsage %a.header; + gi NMTOKEN #REQUIRED + occurs NMTOKEN #IMPLIED + wsd CDATA #IMPLIED > + + References declaration + +<!ELEMENT refsDecl (#PCDATA) > +<!ATTLIST refsDecl %a.header; + doctype NMTOKEN #IMPLIED > + + Classify texts declaration + +<!ELEMENT classDecl (taxonomy+) > +<!ATTLIST classDecl %a.header; > + +<!ELEMENT taxonomy (category+) > +<!ATTLIST taxonomy %a.header; > + +<!ELEMENT category (catDesc, category*) > +<!ATTLIST category + id ID #REQUIRED + n CDATA #IMPLIED + lang IDREF #IMPLIED > + +<!ELEMENT catDesc (#PCDATA) > +<!ATTLIST catDesc %a.header; > + +--> + +<!-- Profile description --> +<!-- creation, langUsage, wsdUsage, annotations: usunięte, dodaję textDesc --> +<!-- profileDesc nie uwzględnione w x2XCES --> + +<!ELEMENT profileDesc ( textClass?, translations?, + textDesc) > +<!ATTLIST profileDesc %a.header; > + +<!-- Creation element --> +<!-- jak to rozumieć? +3.5.1. The <creation> element +This element is used to record details concerning the origination of the text, whether or not covered elsewhere. +http://www.cs.vassar.edu/CES/CES1-3.html#ToC14 --> +<!-- +<!ELEMENT creation (#PCDATA ) > +<!ATTLIST creation %a.header; + date CDATA #REQUIRED > + --> + +<!-- wylatuje + +<!ELEMENT langUsage (language+ ) > +<!ATTLIST langUsage %a.header; > + +<!ELEMENT language (#PCDATA) > +<!ATTLIST language + id ID #IMPLIED + wsd CDATA #IMPLIED + n CDATA #IMPLIED + type CDATA #IMPLIED + iso639 CDATA #REQUIRED > +--> + + +<!-- wylatuje + + +<!ELEMENT wsdUsage (writingSystem+) > +<!ATTLIST wsdUsage %a.header; > + +<!ELEMENT writingSystem (#PCDATA) > +<!ATTLIST writingSystem + id ID #IMPLIED + lang CDATA #IMPLIED + wsd ENTITY #IMPLIED + n CDATA #IMPLIED > + --> +<!-- Text Class --> +<!-- catRef: usunięte --> + +<!ELEMENT textClass (h.keywords) > +<!ATTLIST textClass %a.header; + %a.declarable; > +<!-- usunięte +<!ELEMENT catRef EMPTY > +<!ATTLIST catRef %a.header; + target IDREFS #REQUIRED + scheme CDATA #IMPLIED > +--> + +<!ELEMENT h.keywords (keyTerm+) > +<!ATTLIST h.keywords %a.header; > + +<!ELEMENT keyTerm (#PCDATA) > +<!ATTLIST keyTerm %a.header; > + +<!-- Translations --> +<!-- ulega gruntownej przeróbce, dodany nieistniejąca w TEI i CES atrybut _translated_--> + +<!ELEMENT translations (translation, translator+)? > +<!ATTLIST translations + %a.header; + translated (y | n) "n" > + +<!-- zmienione wsd na #IMPLIED --> + +<!ELEMENT translation (#PCDATA) > +<!ATTLIST translation + id ID #IMPLIED + lang CDATA #REQUIRED + wsd CDATA #IMPLIED + n CDATA #IMPLIED + trans.loc ENTITY #IMPLIED > + +<!ELEMENT translator (#PCDATA) > +<!ATTLIST translator %a.header; > + +<!-- Annotations --> +<!-- usunięte + +<!ELEMENT annotations (annotation+) > +<!ATTLIST annotations %a.header; > + +<!ELEMENT annotation (#PCDATA) > +<!ATTLIST annotation %a.header; + type CDATA #IMPLIED + ann.loc ENTITY #IMPLIED + trans.loc ENTITY #IMPLIED > +--> +<!-- domain and channel added by rg. Domain shall be used to place the name of the colunm in the newspaper, although it is not exactly what it is intended for in TEI--> +<!ELEMENT textDesc (channel, domain?) > + +<!ATTLIST textDesc + %a.global; + %a.declarable; > + +<!-- dodaję channel --> + +<!ELEMENT channel (#PCDATA) > +<!ATTLIST channel + %a.global; > +<!-- dodaję domain --> +<!ELEMENT domain (#PCDATA) > + + +<!-- Revision description --> + +<!ELEMENT revisionDesc (change+) > +<!ATTLIST revisionDesc %a.header; > + +<!ELEMENT change (changeDate, respName, h.item+) > +<!ATTLIST change %a.header; > + +<!ELEMENT changeDate (#PCDATA) > +<!ATTLIST changeDate %a.header; + value CDATA #IMPLIED > + +<!ELEMENT h.item (#PCDATA) > +<!ATTLIST h.item %a.header; > + + -- GitLab