diff options
| author | Bryan Newbold <bnewbold@archive.org> | 2021-10-21 13:31:27 -0700 |
|---|---|---|
| committer | Bryan Newbold <bnewbold@archive.org> | 2021-10-21 13:31:27 -0700 |
| commit | 2f3fd33c33f12b4426072a0279de85ff797611fe (patch) | |
| tree | 089d0eb973ae78c9750ee57239950fe88feba927 /tests/files/small.xml | |
| download | grobid_tei_xml-2f3fd33c33f12b4426072a0279de85ff797611fe.tar.gz grobid_tei_xml-2f3fd33c33f12b4426072a0279de85ff797611fe.zip | |
init project from existing code and tests in sandcrawler, fatcat-scholar, fuzzycat, etc
Diffstat (limited to 'tests/files/small.xml')
| -rw-r--r-- | tests/files/small.xml | 120 |
1 files changed, 120 insertions, 0 deletions
diff --git a/tests/files/small.xml b/tests/files/small.xml new file mode 100644 index 0000000..4de4059 --- /dev/null +++ b/tests/files/small.xml @@ -0,0 +1,120 @@ +<?xml version="1.0" encoding="UTF-8"?> +<TEI xmlns="http://www.tei-c.org/ns/1.0" +xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" +xsi:schemaLocation="http://www.tei-c.org/ns/1.0 /srv/grobid/grobid-0.5.1/grobid-home/schemas/xsd/Grobid.xsd" + xmlns:xlink="http://www.w3.org/1999/xlink"> + <teiHeader xml:lang="en"> + <encodingDesc> + <appInfo> + <application version="0.5.1-SNAPSHOT" ident="GROBID" when="2018-04-02T00:31+0000"> + <ref target="https://github.com/kermitt2/grobid">GROBID - A machine learning software for extracting information from scholarly documents</ref> + </application> + </appInfo> + </encodingDesc> + <fileDesc> + <titleStmt> + <title level="a" type="main">Dummy Example File</title> + </titleStmt> + <publicationStmt> + <publisher/> + <availability status="unknown"><licence/></availability> + <date type="published" when="2000">2000</date> + </publicationStmt> + <sourceDesc> + <biblStruct> + <analytic> + <author> + <persName xmlns="http://www.tei-c.org/ns/1.0"><forename type="first">Brewster</forename><surname>Kahle</surname></persName> + <affiliation key="aff0"> + <orgName type="department">Faculty ofAgricultrial Engineering</orgName> + <orgName type="laboratory">Plant Physiology Laboratory</orgName> + <orgName type="institution">Technion-Israel Institute of Technology</orgName> + <address> + <postCode>32000</postCode> + <settlement>Haifa</settlement> + <country key="IL">Israel</country> + </address> + </affiliation> + </author> + <author> + <persName xmlns="http://www.tei-c.org/ns/1.0"><forename type="first">J</forename><surname>Doe</surname></persName> + </author> + <author> + <affiliation key="aff0"> + <orgName type="institution">Internet Archive</orgName> + </affiliation> + </author> + <title level="a" type="main">Dummy Example File</title> + </analytic> + <monogr> + <title level="m">Dummy Example File. Journal of Fake News. pp. 1-2. ISSN 1234-5678</title> + <imprint> + <date type="published" when="2000">2000</date> + </imprint> + </monogr> + </biblStruct> + </sourceDesc> + </fileDesc> + <profileDesc> + <textClass> + <keywords> + <term>Fake Data</term> + </keywords> + </textClass> + <abstract> + <p>Everything you ever wanted to know about nothing</p> + </abstract> + </profileDesc> + </teiHeader> + <text xml:lang="en"> + <body> +<div xmlns="http://www.tei-c.org/ns/1.0"><head n="1">Introduction</head><p> +Everything starts somewhere, as somebody<ref type="bibr" target="#b0">[1]</ref> once said.</p></div> + +<div xmlns="http://www.tei-c.org/ns/1.0"><head n="2">In Depth</head></div> +<div xmlns="http://www.tei-c.org/ns/1.0"><head n="2.1">Meat</head><p> +You know, for kids.</p></div> +<div xmlns="http://www.tei-c.org/ns/1.0"><head n="2.2">Potatos</head><p> +QED.</p></div> + </body> + <back> + <div type="references"> + + <listBibl> + +<biblStruct xml:id="b0"> + <analytic> + <title level="a" type="main">Everything is Wonderful</title> + <author> + <persName xmlns="http://www.tei-c.org/ns/1.0"><forename type="middle">A</forename><surname>Seaperson</surname></persName> + </author> + </analytic> + <monogr> + <title level="j">Letters in the Alphabet</title> + <imprint> + <biblScope unit="volume">20</biblScope> + <biblScope unit="page" from="1" to="11" /> + <date type="published" when="2001" /> + </imprint> + </monogr> +</biblStruct> + +<biblStruct xml:id="b1"> + <analytic> + <title level="a" type="main">All about Facts</title> + </analytic> + <monogr> + <title level="j">The Dictionary</title> + <imprint> + <biblScope unit="volume">14</biblScope> + <date type="published" when="2011-03-28" /> + </imprint> + </monogr> + <note>None</note> +</biblStruct> + + </listBibl> + </div> + </back> + </text> +</TEI> |