Skip to content

Added initial PressMint-ES files #28

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
x2gg wants to merge 12 commits into
base: data
Choose a base branch
from
Open

Added initial PressMint-ES files #28

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
12 commits
Select commit Hold shift + click to select a range
0f4e673
Added initial PressMint-ES files
x2gg Nov 24, 2025
17d0cbe
fixed added newpar_id to ARGIA19210501.json
x2gg Nov 24, 2025
1eb7c59
remove misplaced file
x2gg Nov 25, 2025
d6bbde9
fix tittle and mte:Z
x2gg Nov 25, 2025
6ea5944
Merge branch 'data' into data
matyaskopp Nov 25, 2025
42bcf37
Merge branch 'data' into data
x2gg Nov 25, 2025
9cb3075
Merge branch 'data' into data
matyaskopp Nov 25, 2025
94f86f5
Rename folder from sources to Sources
x2gg Nov 27, 2025
ee108fb
Fix folder name
x2gg Nov 27, 2025
6d2ce44
Merge branch 'data' into data
matyaskopp Nov 29, 2025
f78bd9b
Merge branch 'data' into data
matyaskopp Jan 27, 2026
e322cd3
Merge branch 'data' into data
matyaskopp Feb 2, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9,014 changes: 9,014 additions & 0 deletions Samples/PressMint-ES/1921/PressMint-ES_1921-05-01-ARGIA1920501.ana.xml
View file
Open in desktop

Large diffs are not rendered by default.

53 changes: 53 additions & 0 deletions Samples/PressMint-ES/1921/PressMint-ES_1921-05-01-ARGIA1920501.xml
View file
Open in desktop

Large diffs are not rendered by default.

168 changes: 168 additions & 0 deletions Samples/PressMint-ES/PressMint-ES.ana.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,168 @@
<?xml version="1.0" encoding="UTF-8"?>
<teiCorpus xmlns="http://www.tei-c.org/ns/1.0" xml:id="PressMint-ES.ana" xml:lang="eu">
<teiHeader>
<fileDesc>
<titleStmt>
<title xml:lang="eu">Euskal Herriko prentsa historikoa: PressMint ES-EU [PressMint Laginketa]</title>
<title xml:lang="es">Corpus histórico de prensa vascaCorpus histórico de prensa vasca: PressMint ES-EU [PressMint Muestra]</title>
<title xml:lang="en">Basque historical newspaper corpus PressMint-ES-EU [PressMint SAMPLE]</title>

<respStmt>
<persName >Xabier Goenaga</persName>
<resp xml:lang="eu">PressMint TEI XML kodeketa</resp>
<resp xml:lang="es">Codificación PressMint TEI XML</resp>
<resp xml:lang="en">PressMint TEI XML corpus encoding</resp>
</respStmt>

<respStmt>
<persName ref="https://orcid.org/0000-0002-1616-5665">Ainara Estarrona Ibarloza</persName>
<persName ref="https://orcid.org/0000-0003-0124-3007">Aritz Farwell</persName>

<resp xml:lang="eu">Atzoko Prentsa sorburu-corpusa prestatu</resp>
<resp xml:lang="es">Preparación del corpus original Atzoko Prentsa</resp>
<resp xml:lang="en">Preparation of source Atzoko Prentsa corpus</resp>
</respStmt>

<funder>
<orgName xml:lang="eu">CLARIN ikerketa-azpiegitura</orgName>
<orgName xml:lang="es">Infraestructura de investigación CLARIN</orgName>
<orgName xml:lang="en">The CLARIN research infrastructure</orgName>
</funder>

<funder>
<orgName>CLARIN.ES</orgName>
</funder>
</titleStmt>
<extent><!--These numbers do not reflect the size of the sample!-->
<measure unit="texts" quantity="2245" xml:lang="en">2,245 texts</measure>
<measure unit="paragraphs" quantity="518053" xml:lang="en">518,053 paragraphs</measure>
<measure unit="words" quantity="18594041" xml:lang="en">18,594,041 words</measure>
</extent>

<publicationStmt>
<publisher>
<orgName xml:lang="eu">CLARIN ikerketa-azpiegitura</orgName>
<orgName xml:lang="es">Infraestructura de investigación CLARIN</orgName>
<orgName xml:lang="en">CLARIN research infrastructure</orgName>
<ref target="https://www.clarin.eu/">www.clarin.eu</ref>
</publisher>
<availability status="free">
<licence>http://creativecommons.org/licenses/by/4.0/</licence>
<p xml:lang="eu">
Lan hau <ref target="http://creativecommons.org/licenses/by/4.0/">
Creative Commons Aitortu 4.0 Nazioartekoa
</ref> lizentziapean banatzen da.
</p>
<p xml:lang="es">
Esta obra se distribuye bajo la
<ref target="http://creativecommons.org/licenses/by/4.0/">
Licencia Creative Commons Atribución 4.0 Internacional</ref>.
</p>
<p xml:lang="en">
This work is licensed under the
<ref target="http://creativecommons.org/licenses/by/4.0/">
Creative Commons Attribution 4.0 International License</ref>.
</p>
</availability>
<date when="2025-11-24">2025-11-24</date>
</publicationStmt>
<sourceDesc>
<bibl>
<author>Estarrona Ibarloza, Ainara </author>
<author>Farwell, Aritz</author>

<title type="main" xml:lang="eu">Euskal Herriko prentsa historikoa</title>
<title type="main" xml:lang="es">Corpus histórico de prensa vasca</title>

<date>2025</date>
</bibl>
</sourceDesc>
</fileDesc>
<encodingDesc>
<projectDesc>
<p xml:lang="eu">
<ref target="https://www.clarin.eu/pressmint">PressMint</ref> proiektuak
Europar prentsa historikoaren corpusetan oinarritutako
datu multilingue eta egituratuak sortzea du helburu,
<ref target="https://clarin-eric.github.io/PressMint/">PressMint jarraibideen</ref> arabera.
</p>

<p xml:lang="es">
El proyecto <ref target="https://www.clarin.eu/pressmint">PressMint</ref>
tiene como objetivo crear un conjunto multilingüe de
corpus de prensa histórica, uniformemente codificados
siguiendo las <ref target="https://clarin-eric.github.io/PressMint/">directrices PressMint</ref>.
</p>

<p xml:lang="en">
The PressMint project aims to create multilingual and
uniformly encoded historical newspapers corpora following
the <ref target="https://clarin-eric.github.io/PressMint/">PressMint encoding guidelines</ref>.
</p>
</projectDesc>

<editorialDecl>
<quotation>
<p xml:lang="eu">Komatxoak testuan utzi dira eta ez dira markatu.</p>
<p xml:lang="es">Las comillas se mantienen en el texto y no se han marcado.</p>
</quotation>

<hyphenation>
<p xml:lang="eu">Lerro amaierako marratzeak automatikoki konpondu dira neurri batean.</p>
<p xml:lang="es">Las palabras divididas por guiones al final de línea han sido reconstruidas en parte.</p>
</hyphenation>

<normalization>
<p xml:lang="eu">Testua ez da normalizatu, espazioak salbu.</p>
<p xml:lang="es">El texto no ha sido normalizado, salvo el espaciado.</p>
</normalization>

</editorialDecl>
<tagsDecl><!--These numbers do not reflect the size of the sample!-->
<namespace name="http://www.tei-c.org/ns/1.0">
<tagUsage gi="body" occurs="247"/>
<tagUsage gi="name" occurs="135263"/>
<tagUsage gi="p" occurs="57862"/>
<tagUsage gi="pb" occurs="1063"/>
<tagUsage gi="pc" occurs="472792"/>
<tagUsage gi="s" occurs="149907"/>
<tagUsage gi="text" occurs="247"/>
<tagUsage gi="w" occurs="1973547"/>
</namespace>
</tagsDecl>
<classDecl>
<xi:include xmlns:xi="http://www.w3.org/2001/XInclude" href="PressMint-taxonomy-OCR.xml"/>
<xi:include xmlns:xi="http://www.w3.org/2001/XInclude" href="PressMint-taxonomy-NER.ana.xml"/>
</classDecl>
<appInfo>
<application version="2.0" ident="udpipe">
<label>UDPipe</label>
<desc xml:lang="en">Linguistic processing with ud, available from <ref target="https://github.com/ufal/udpipe/tree/udpipe-2">https://github.com/ufal/udpipe/tree/udpipe-2</ref>.</desc>
</application>
</appInfo>
</encodingDesc>
<profileDesc>
<settingDesc>
<setting>
<date from="1921" to="1921">1921- 1921</date>
</setting>
</settingDesc>
<langUsage>
<language ident="eu" xml:lang="eu">euskara</language>
<language ident="eu" xml:lang="es">euskera</language>
<language ident="eu" xml:lang="en">Basque</language>
<language ident="es" xml:lang="eu">gaztelania</language>
<language ident="es" xml:lang="es">español</language>
<language ident="es" xml:lang="en">Spanish</language>
<language ident="en" xml:lang="eu">ingelesa</language>
<language ident="en" xml:lang="es">inglés</language>
<language ident="en" xml:lang="en">English</language>
</langUsage>
</profileDesc>
<revisionDesc>
<change when="2025-11-22">Adapted to EU + ES PressMint corpus.</change>
</revisionDesc>
</teiHeader>
<xi:include xmlns:xi="http://www.w3.org/2001/XInclude" href="1921/PressMint-ES_1921-05-01-ARGIA1920501.ana.xml"/>

</teiCorpus>
157 changes: 157 additions & 0 deletions Samples/PressMint-ES/PressMint-ES.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,157 @@
<?xml version="1.0" encoding="UTF-8"?>
<teiCorpus xmlns="http://www.tei-c.org/ns/1.0" xml:id="PressMint-EU-ES" xml:lang="eu">
<teiHeader>
<fileDesc>
<titleStmt>
<title xml:lang="eu">Euskal Herriko prentsa historikoa: PressMint ES-EU [PressMint Laginketa]</title>
<title xml:lang="es">Corpus histórico de prensa vascaCorpus histórico de prensa vasca: PressMint ES-EU [PressMint Muestra]</title>
<title xml:lang="en">Basque historical newspaper corpus PressMint-ES-EU [PressMint SAMPLE]</title>

<respStmt>
<persName >Xabier Goenaga</persName>
<resp xml:lang="eu">PressMint TEI XML kodeketa</resp>
<resp xml:lang="es">Codificación PressMint TEI XML</resp>
<resp xml:lang="en">PressMint TEI XML corpus encoding</resp>
</respStmt>

<respStmt>
<persName ref="https://orcid.org/0000-0002-1616-5665">Ainara Estarrona Ibarloza</persName>
<persName ref="https://orcid.org/0000-0003-0124-3007">Aritz Farwell</persName>

<resp xml:lang="eu">Atzoko Prentsa sorburu-corpusa prestatu</resp>
<resp xml:lang="es">Preparación del corpus original Atzoko Prentsa</resp>
<resp xml:lang="en">Preparation of source Atzoko Prentsa corpus</resp>
</respStmt>

<funder>
<orgName xml:lang="eu">CLARIN ikerketa-azpiegitura</orgName>
<orgName xml:lang="es">Infraestructura de investigación CLARIN</orgName>
<orgName xml:lang="en">The CLARIN research infrastructure</orgName>
</funder>

<funder>
<orgName>CLARIN.ES</orgName>
</funder>
</titleStmt>

<editionStmt>
<edition>1.0</edition>
</editionStmt>

<!-- <extent>
<measure unit="texts" quantity="2245">2245 testu</measure>
<measure unit="paragraphs" quantity="502642">502642 paragrafo</measure>
<measure unit="words" quantity="18594041">18594041 hitz</measure>
</extent> -->

<publicationStmt>
<publisher>
<orgName xml:lang="eu">CLARIN ikerketa-azpiegitura</orgName>
<orgName xml:lang="es">Infraestructura de investigación CLARIN</orgName>
<orgName xml:lang="en">CLARIN research infrastructure</orgName>
<ref target="https://www.clarin.eu/">www.clarin.eu</ref>
</publisher>

<availability status="free">
<licence>http://creativecommons.org/licenses/by/4.0/</licence>

<p xml:lang="eu">
Lan hau <ref target="http://creativecommons.org/licenses/by/4.0/">
Creative Commons Aitortu 4.0 Nazioartekoa
</ref> lizentziapean banatzen da.
</p>

<p xml:lang="es">
Esta obra se distribuye bajo la
<ref target="http://creativecommons.org/licenses/by/4.0/">
Licencia Creative Commons Atribución 4.0 Internacional</ref>.
</p>

<p xml:lang="en">
This work is licensed under the <ref target="http://creativecommons.org/licenses/by/4.0/">
Creative Commons Attribution 4.0 International License</ref>.
</p>
</availability>
</publicationStmt>

<sourceDesc>
<bibl>
<author>Estarrona Ibarloza, Ainara </author>
<author>Farwell, Aritz</author>

<title type="main" xml:lang="eu">Euskal Herriko prentsa historikoa</title>
<title type="main" xml:lang="es">Corpus histórico de prensa vasca</title>

<date>2025</date>
</bibl>
</sourceDesc>
</fileDesc>

<encodingDesc>
<projectDesc>
<p xml:lang="eu">
<ref target="https://www.clarin.eu/pressmint">PressMint</ref> proiektuak Europar prentsa historikoaren corpusetan oinarritutako datu multilingue eta egituratuak sortzea du helburu,
<ref target="https://clarin-eric.github.io/PressMint/">PressMint jarraibideen</ref> arabera.
</p>

<p xml:lang="es">
El proyecto <ref target="https://www.clarin.eu/pressmint">PressMint</ref> tiene como objetivo crear un conjunto multilingüe de corpus de prensa histórica, uniformemente codificados
siguiendo las <ref target="https://clarin-eric.github.io/PressMint/">directrices PressMint</ref>.
</p>

<p xml:lang="en">
The PressMint project aims to create multilingual and uniformly encoded historical newspapers corpora following the <ref target="https://clarin-eric.github.io/PressMint/">PressMint encoding guidelines</ref>.
</p>
</projectDesc>

<editorialDecl>
<quotation>
<p xml:lang="eu">Komatxoak testuan utzi dira eta ez dira markatu.</p>
<p xml:lang="es">Las comillas se mantienen en el texto y no se han marcado.</p>
</quotation>

<hyphenation>
<p xml:lang="eu">Lerro amaierako marratzeak automatikoki konpondu dira neurri batean.</p>
<p xml:lang="es">Las palabras divididas por guiones al final de línea han sido reconstruidas en parte.</p>
</hyphenation>

<normalization>
<p xml:lang="eu">Testua ez da normalizatu, espazioak salbu.</p>
<p xml:lang="es">El texto no ha sido normalizado, salvo el espaciado.</p>
</normalization>

</editorialDecl>

<classDecl>
<xi:include xmlns:xi="http://www.w3.org/2001/XInclude" href="PressMint-taxonomy-OCR.xml"/>
</classDecl>
</encodingDesc>

<profileDesc>
<settingDesc>
<setting>
<date from="1921" to="1921">1921–1921</date>
</setting>
</settingDesc>

<langUsage>
<language ident="eu" xml:lang="eu">euskara</language>
<language ident="eu" xml:lang="es">euskera</language>
<language ident="eu" xml:lang="en">Basque</language>
<language ident="es" xml:lang="eu">gaztelania</language>
<language ident="es" xml:lang="es">español</language>
<language ident="es" xml:lang="en">Spanish</language>
<language ident="en" xml:lang="eu">ingelesa</language>
<language ident="en" xml:lang="es">inglés</language>
<language ident="en" xml:lang="en">English</language>
</langUsage>
</profileDesc>

<revisionDesc>
<change when="2025-11-22">Adapted to EU + ES PressMint corpus.</change>
</revisionDesc>
</teiHeader>

<!-- Ejemplo de includes adaptados a EU-ES -->
<xi:include xmlns:xi="http://www.w3.org/2001/XInclude" href="1921/PressMint-ES_1921-05-01-ARGIA1920501.xml"/>
</teiCorpus>
32 changes: 32 additions & 0 deletions Samples/PressMint-ES/PressMint-taxonomy-NER.ana.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,32 @@
<?xml version="1.0" encoding="UTF-8"?>
<taxonomy xmlns="http://www.tei-c.org/ns/1.0" xml:id="PressMint-taxonomy-NER">

<!-- Pertsona / Persona / Person -->
<category xml:id="PER">
<catDesc xml:lang="eu">Pertsona</catDesc>
<catDesc xml:lang="es">Persona</catDesc>
<catDesc xml:lang="en">Person</catDesc>
</category>

<!-- Erakundea / Organización / Organization -->
<category xml:id="ORG">
<catDesc xml:lang="eu">Erakundea</catDesc>
<catDesc xml:lang="es">Organización</catDesc>
<catDesc xml:lang="en">Organization</catDesc>
</category>

<!-- Lekua / Lugar / Location -->
<category xml:id="LOC">
<catDesc xml:lang="eu">Lekua</catDesc>
<catDesc xml:lang="es">Lugar</catDesc>
<catDesc xml:lang="en">Location</catDesc>
</category>

<!-- Mota ezberdinak / Miscelánea / Miscellaneous -->
<category xml:id="MISC">
<catDesc xml:lang="eu">Mota ezberdinak</catDesc>
<catDesc xml:lang="es">Miscelánea</catDesc>
<catDesc xml:lang="en">Miscellaneous</catDesc>
</category>

</taxonomy>
16 changes: 16 additions & 0 deletions Samples/PressMint-ES/PressMint-taxonomy-OCR.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,16 @@
<?xml version="1.0" encoding="UTF-8"?>
<taxonomy xmlns="http://www.tei-c.org/ns/1.0" xml:id="PressMint-taxonomy-OCR" xml:lang="mul">
<desc xml:lang="en"><term>OCR quality</term></desc>
<desc xml:lang="eu"><term>OCR kalitatea</term></desc>
<desc xml:lang="es"><term>Calidad OCR</term></desc>
<category xml:id="quality.low">
<catDesc xml:lang="en"><term>low</term></catDesc>
<catDesc xml:lang="eu"><term>baxua</term></catDesc>
<catDesc xml:lang="es"><term>bajo</term></catDesc>
</category>
<category xml:id="quality.high">
<catDesc xml:lang="en"><term>high</term></catDesc>
<catDesc xml:lang="eu"><term>altua</term></catDesc>
<catDesc xml:lang="es"><term>alto</term></catDesc>
</category>
</taxonomy>
1 change: 1 addition & 0 deletions Samples/PressMint-ES/Sources/ARGIA19210501.json
View file
Open in desktop

Large diffs are not rendered by default.

Loading