-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Add more simple timestamps extraction tests #9
- Loading branch information
Showing
7 changed files
with
815 additions
and
6 deletions.
There are no files selected for viewing
16 changes: 16 additions & 0 deletions
16
test/MetadataExtraction/examples/expected/expectedTimestampsMultipleTimelines.txt
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,16 @@ | ||
| ---SPEECH--- | ||
| ID: timestampsMultipleTimelines.u1 | ||
| author: #personX | ||
| role: #roleX | ||
| when: 2013-11-25 | ||
| tokens: 13 | ||
| sentences: 1 | ||
| named entity refferences: 0 | ||
| total duration: 1030.0 | ||
| total spoken: 700.0 | ||
| time silent: 330.0 | ||
| time unknown: 0 | ||
| unaligned tokens: 0 | ||
| earliest timeline: 2024-10-21T14:49:00 | ||
| latest timeline: 2024-10-21T15:09:00 | ||
|
|
16 changes: 16 additions & 0 deletions
16
test/MetadataExtraction/examples/expected/expectedTimestampsNamesAndDates.txt
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,16 @@ | ||
| ---SPEECH--- | ||
| ID: timestampsNamesAndDates.u1 | ||
| author: #personX | ||
| role: #roleX | ||
| when: 2013-11-25 | ||
| tokens: 13 | ||
| sentences: 1 | ||
| named entity refferences: 2 | ||
| total duration: 1040.0 | ||
| total spoken: 700.0 | ||
| time silent: 340.0 | ||
| time unknown: 0 | ||
| unaligned tokens: 0 | ||
| earliest timeline: 2024-10-21T14:49:00 | ||
| latest timeline: 2024-10-21T14:49:00 | ||
|
|
16 changes: 16 additions & 0 deletions
16
test/MetadataExtraction/examples/expected/expectedTimestampsSimple.txt
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,16 @@ | ||
| ---SPEECH--- | ||
| ID: timestampsSimple.u1 | ||
| author: #personX | ||
| role: #roleX | ||
| when: 2013-11-25 | ||
| tokens: 13 | ||
| sentences: 1 | ||
| named entity refferences: 0 | ||
| total duration: 1040.0 | ||
| total spoken: 700.0 | ||
| time silent: 340.0 | ||
| time unknown: 0 | ||
| unaligned tokens: 0 | ||
| earliest timeline: 2024-10-21T14:49:00 | ||
| latest timeline: 2024-10-21T14:49:00 | ||
|
|
255 changes: 255 additions & 0 deletions
255
test/MetadataExtraction/examples/inputs/timestampsMultipleTimelines.xml
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,255 @@ | ||
| <?xml version="1.0" encoding="UTF-8"?> | ||
| <TEI xmlns="http://www.tei-c.org/ns/1.0" | ||
| xml:id="ps2013-001-01-000-999.ana" | ||
| xml:lang="cs" | ||
| ana="#parla.agenda"> | ||
| <teiHeader> | ||
| <fileDesc> | ||
| <titleStmt> | ||
| <title type="main" xml:lang="cs">Český parlamentní korpus, Poslanecká sněmovna, 2013-11-25 ps2013-001-01-000-999 [ParCzech.ana]</title> | ||
| <title type="main" xml:lang="en">Czech parliamentary corpus, Chamber of Deputies, 2013-11-25 ps2013-001-01-000-999 [ParCzech.ana]</title> | ||
| <title type="sub" xml:lang="cs">Parlament České republiky, Poslanecká sněmovna, 2013-11-25, Začátek schůze Poslanecké sněmovny 25. listopadu 2013 ve 14.05 hodin Přítomno: 199 poslanců</title> | ||
| <title type="sub" xml:lang="en">Parliament of the Czech Republic, Chamber of Deputies, 2013-11-25</title> | ||
| <title xml:lang="cs" type="short">Začátek schůze Poslanecké sněmovny 25. listopadu 2013 ve 14.05 hodin Přítomno: 199 poslanců</title> | ||
| <meeting ana="#parla.term #parla.lower #parliament.PSP7" n="ps2013">ps2013</meeting> | ||
| <meeting ana="#parla.meeting #parla.lower" n="ps2013/001">ps2013/001</meeting> | ||
| <meeting ana="#parla.sitting #parla.lower" n="ps2013/001/01">ps2013/001/01</meeting> | ||
| <meeting ana="#parla.agenda #parla.lower" n="ps2013/001/999">ps2013/001/999</meeting> | ||
| <respStmt> | ||
| <persName ref="https://orcid.org/0000-0001-7953-8783">Matyáš Kopp</persName> | ||
| <resp xml:lang="en">Data retrieval</resp> | ||
| <resp xml:lang="en">TEI XML corpus encoding</resp> | ||
| <resp xml:lang="en">Linguistic annotation</resp> | ||
| </respStmt> | ||
| <funder> | ||
| <orgName xml:lang="cs">LINDAT/CLARIAH-CZ: Digitální výzkumná infrastruktura pro jazykové technologie, umění a humanitní vědy</orgName> | ||
| <orgName xml:lang="en">LINDAT/CLARIAH-CZ: Digital Research Infrastructure for Language Technologies, Arts and Humanities</orgName> | ||
| </funder> | ||
| </titleStmt> | ||
| <editionStmt> | ||
| <edition>4.0</edition> | ||
| </editionStmt> | ||
| <extent> | ||
| <measure unit="speeches" quantity="1" xml:lang="cs">1 promluv</measure> | ||
| <measure unit="speeches" quantity="1" xml:lang="en">1 speeches</measure> | ||
| <measure unit="words" quantity="173" xml:lang="cs">173 slov</measure> | ||
| <measure unit="words" quantity="173" xml:lang="en">173 words</measure> | ||
| </extent> | ||
| <publicationStmt> | ||
| <publisher> | ||
| <orgName xml:lang="cs">LINDAT/CLARIAH-CZ: Digitální výzkumná infrastruktura pro jazykové technologie, umění a humanitní vědy</orgName> | ||
| <orgName xml:lang="en">LINDAT/CLARIAH-CZ: Digital Research Infrastructure for Language Technologies, Arts and Humanities</orgName> | ||
| <ref target="https://www.lindat.cz">www.lindat.cz</ref> | ||
| </publisher> | ||
| <idno type="URI" subtype="handle">http://hdl.handle.net/11234/1-5360</idno> | ||
| <availability status="free"> | ||
| <licence>https://creativecommons.org/publicdomain/zero/1.0/</licence> | ||
| <p xml:lang="en">This work is licensed under the <ref target="https://creativecommons.org/publicdomain/zero/1.0/">CC0 1.0 Universal (CC0 1.0) Public Domain Dedication</ref>.</p> | ||
| </availability> | ||
| <date when="2024-01-26">2024-01-26</date> | ||
| </publicationStmt> | ||
| <sourceDesc> | ||
| <bibl> | ||
| <title type="main" xml:lang="cs">Parlament České republiky, Poslanecká sněmovna</title> | ||
| <title type="main" xml:lang="en">Parliament of the Czech Republic, Chamber of Deputies</title> | ||
| <idno type="URI" subtype="parliament">https://www.psp.cz/eknih/2013ps/stenprot/001schuz/s001001.htm</idno> | ||
| <date when="2013-11-25">25.11.2013</date> | ||
| </bibl> | ||
| <recordingStmt> | ||
| <recording type="audio"> | ||
| <media xml:id="ps2013-001-01-000-999.audio1" | ||
| mimeType="audio/mp3" | ||
| source="https://www.psp.cz/eknih/2013ps/audio/2013/11/25/2013112513581412.mp3" | ||
| url="audio/psp/2013/11/25/2013112513581412.mp3"/> | ||
| </recording> | ||
| </recordingStmt> | ||
| </sourceDesc> | ||
| </fileDesc> | ||
| <encodingDesc> | ||
| <projectDesc> | ||
| <p xml:lang="en"> | ||
| <ref target="https://ufal.mff.cuni.cz/parczech">ParCzech</ref> is a project on compiling Czech parliamentary data into annotated corpora. It mostly follows the <ref target="https://www.clarin.eu/parlamint">ParlaMint project's</ref> recommendation, but the data are slightly extended in several ways. Texts contain links to original voting and prints. Except for the 4-class named entities classification, it also includes a more detailed CNEC hierarchical classification. The text in the annotated version is aligned with audio on the token level. And morphological annotation contains pdt tagsed besides UD PoS and features.</p> | ||
| </projectDesc> | ||
| <tagsDecl> | ||
| <namespace name="http://www.tei-c.org/ns/1.0"> | ||
| <tagUsage gi="anchor" occurs="322"/> | ||
| <tagUsage gi="body" occurs="1"/> | ||
| <tagUsage gi="date" occurs="8"/> | ||
| <tagUsage gi="div" occurs="1"/> | ||
| <tagUsage gi="link" occurs="198"/> | ||
| <tagUsage gi="linkGrp" occurs="12"/> | ||
| <tagUsage gi="name" occurs="18"/> | ||
| <tagUsage gi="note" occurs="5"/> | ||
| <tagUsage gi="num" occurs="3"/> | ||
| <tagUsage gi="pb" occurs="1"/> | ||
| <tagUsage gi="pc" occurs="24"/> | ||
| <tagUsage gi="s" occurs="12"/> | ||
| <tagUsage gi="seg" occurs="6"/> | ||
| <tagUsage gi="text" occurs="1"/> | ||
| <tagUsage gi="timeline" occurs="1"/> | ||
| <tagUsage gi="u" occurs="1"/> | ||
| <tagUsage gi="w" occurs="175"/> | ||
| <tagUsage gi="when" occurs="323"/> | ||
| </namespace> | ||
| </tagsDecl> | ||
| </encodingDesc> | ||
| <profileDesc> | ||
| <settingDesc> | ||
| <setting> | ||
| <name type="org">Parlament České republiky - Poslanecká sněmovna</name> | ||
| <name type="address">Sněmovní 176/4</name> | ||
| <name type="city">Praha</name> | ||
| <name key="CZ" type="country">Czech Republic</name> | ||
| <date when="2013-11-25" ana="#parla.sitting">2013-11-25</date> | ||
| </setting> | ||
| </settingDesc> | ||
| </profileDesc> | ||
| </teiHeader> | ||
| <text> | ||
| <body> | ||
| <div> | ||
| <u who="#personX" | ||
| ana="#roleX" | ||
| xml:id="timestampsMultipleTimelines.u1"> | ||
| <seg xml:id="timestampsMultipleTimelines.u1.p1"> | ||
| <s xml:id="timestampsMultipleTimelines.u1.p1.s1"> | ||
| <anchor synch="#timestampsMultipleTimelines.u1.p1.s1.w1.ab"/> | ||
| <w xml:id="timestampsMultipleTimelines.u1.p1.s1.w1">Lorem</w> | ||
| <anchor synch="#timestampsMultipleTimelines.u1.p1.s1.w1.ae"/> | ||
| <anchor synch="#timestampsMultipleTimelines.u1.p1.s1.w2.ab"/> | ||
| <w xml:id="timestampsMultipleTimelines.u1.p1.s1.w2">Ipsum</w> | ||
| <anchor synch="#timestampsMultipleTimelines.u1.p1.s1.w2.ae"/> | ||
| <anchor synch="#timestampsMultipleTimelines.u1.p1.s1.w3.ab"/> | ||
| <w xml:id="timestampsMultipleTimelines.u1.p1.s1.w3">dolor</w> | ||
| <anchor synch="#timestampsMultipleTimelines.u1.p1.s1.w3.ae"/> | ||
| <anchor synch="#timestampsMultipleTimelines.u1.p1.s1.w4.ab"/> | ||
| <w xml:id="timestampsMultipleTimelines.u1.p1.s1.w4">sit</w> | ||
| <anchor synch="#timestampsMultipleTimelines.u1.p1.s1.w4.ae"/> | ||
| <anchor synch="#timestampsMultipleTimelines.u1.p1.s1.w5.ab"/> | ||
| <w xml:id="timestampsMultipleTimelines.u1.p1.s1.w5">amet</w> | ||
| <anchor synch="#timestampsMultipleTimelines.u1.p1.s1.w5.ae"/> | ||
| <pc xml:id="timestampsMultipleTimelines.u1.p1.s1.w6">,</pc> | ||
| <anchor synch="#timestampsMultipleTimelines.u1.p1.s1.w7.ab"/> | ||
| <w xml:id="timestampsMultipleTimelines.u1.p1.s1.w7">consecteur</w> | ||
| <anchor synch="#timestampsMultipleTimelines.u1.p1.s1.w7.ae"/> | ||
| <anchor synch="#timestampsMultipleTimelines.u1.p1.s1.w8.ab"/> | ||
| <w xml:id="timestampsMultipleTimelines.u1.p1.s1.w8">adipiscing</w> | ||
| <anchor synch="#timestampsMultipleTimelines.u1.p1.s1.w8.ae"/> | ||
| <anchor synch="#timestampsMultipleTimelines.u1.p1.s1.w9.ab"/> | ||
| <w xml:id="timestampsMultipleTimelines.u1.p1.s1.w9">elit</w> | ||
| <anchor synch="#timestampsMultipleTimelines.u1.p1.s1.w9.ae"/> | ||
| <pc xml:id="timestampsMultipleTimelines.u1.p1.s1.w10"></pc> | ||
| <anchor synch="#timestampsMultipleTimelines.u1.p1.s1.w11.ab"/> | ||
| <w xml:id="timestampsMultipleTimelines.u1.p1.s1.w11">sed</w> | ||
| <anchor synch="#timestampsMultipleTimelines.u1.p1.s1.w11.ae"/> | ||
| <anchor synch="#timestampsMultipleTimelines.u1.p1.s1.w12.ab"/> | ||
| <w xml:id="timestampsMultipleTimelines.u1.p1.s1.w12">do</w> | ||
| <anchor synch="#timestampsMultipleTimelines.u1.p1.s1.w12.ae"/> | ||
| <anchor synch="#timestampsMultipleTimelines.u1.p1.s1.w13.ab"/> | ||
| <w xml:id="timestampsMultipleTimelines.u1.p1.s1.w13">eiusmod</w> | ||
| <anchor synch="#timestampsMultipleTimelines.u1.p1.s1.w13.ae"/> | ||
| <anchor synch="#timestampsMultipleTimelines.u1.p1.s1.w14.ab"/> | ||
| <w xml:id="timestampsMultipleTimelines.u1.p1.s1.w14">tempor</w> | ||
| <anchor synch="#timestampsMultipleTimelines.u1.p1.s1.w14.ae"/> | ||
| <anchor synch="#timestampsMultipleTimelines.u1.p1.s1.w15.ab"/> | ||
| <w xml:id="timestampsMultipleTimelines.u1.p1.s1.w15">incididunt</w> | ||
| <anchor synch="#timestampsMultipleTimelines.u1.p1.s1.w15.ae"/> | ||
| </s> | ||
| </seg> | ||
| </u> | ||
| </div> | ||
| <timeline unit="ms" | ||
| origin="#timestampsMultipleTimelines.audio1.origin" | ||
| corresp="#timestampsMultipleTimelines.audio1" | ||
| cert="0"> | ||
| <when xml:id="timestampsMultipleTimelines.audio1.origin" | ||
| absolute="2024-10-21T14:49:00"/> | ||
| <when xml:id="timestampsMultipleTimelines.u1.p1.s1.w1.ab" | ||
| interval="100000.0" | ||
| since="#timestampsMultipleTimelines.audio1.origin"/> | ||
| <when xml:id="timestampsMultipleTimelines.u1.p1.s1.w1.ae" | ||
| interval="100050.0" | ||
| since="#timestampsMultipleTimelines.audio1.origin"/> | ||
| <when xml:id="timestampsMultipleTimelines.u1.p1.s1.w2.ab" | ||
| interval="100090.0" | ||
| since="#timestampsMultipleTimelines.audio1.origin"/> | ||
| <when xml:id="timestampsMultipleTimelines.u1.p1.s1.w2.ae" | ||
| interval="100140.0" | ||
| since="#timestampsMultipleTimelines.audio1.origin"/> | ||
| <when xml:id="timestampsMultipleTimelines.u1.p1.s1.w3.ab" | ||
| interval="100150.0" | ||
| since="#timestampsMultipleTimelines.audio1.origin"/> | ||
| <when xml:id="timestampsMultipleTimelines.u1.p1.s1.w3.ae" | ||
| interval="100200.0" | ||
| since="#timestampsMultipleTimelines.audio1.origin"/> | ||
| <when xml:id="timestampsMultipleTimelines.u1.p1.s1.w4.ab" | ||
| interval="100230.0" | ||
| since="#timestampsMultipleTimelines.audio1.origin"/> | ||
| <when xml:id="timestampsMultipleTimelines.u1.p1.s1.w4.ae" | ||
| interval="100260.0" | ||
| since="#timestampsMultipleTimelines.audio1.origin"/> | ||
| <when xml:id="timestampsMultipleTimelines.u1.p1.s1.w5.ab" | ||
| interval="100310.0" | ||
| since="#timestampsMultipleTimelines.audio1.origin"/> | ||
| <when xml:id="timestampsMultipleTimelines.u1.p1.s1.w5.ae" | ||
| interval="100350.0" | ||
| since="#timestampsMultipleTimelines.audio1.origin"/> | ||
| <when xml:id="timestampsMultipleTimelines.u1.p1.s1.w7.ab" | ||
| interval="100390.0" | ||
| since="#timestampsMultipleTimelines.audio1.origin"/> | ||
| <when xml:id="timestampsMultipleTimelines.u1.p1.s1.w7.ae" | ||
| interval="100500.0" | ||
| since="#timestampsMultipleTimelines.audio1.origin"/> | ||
| </timeline> | ||
| <timeline unit="ms" | ||
| origin="#timestampsMultipleTimelines.audio2.origin" | ||
| corresp="#timestampsMultipleTimelines" | ||
| cert="0"> | ||
| <when xml:id="timestampsMultipleTimelines.audio2.origin" | ||
| absolute="2024-10-21T15:09:00"/> | ||
| <when xml:id="timestampsMultipleTimelines.u1.p1.s1.w8.ab" | ||
| interval="100510.0" | ||
| since="#timestampsMultipleTimelines.audio2.origin"/> | ||
| <when xml:id="timestampsMultipleTimelines.u1.p1.s1.w8.ae" | ||
| interval="100610.0" | ||
| since="#timestampsMultipleTimelines.audio2.origin"/> | ||
| <when xml:id="timestampsMultipleTimelines.u1.p1.s1.w9.ab" | ||
| interval="100610.0" | ||
| since="#timestampsMultipleTimelines.audio2.origin"/> | ||
| <when xml:id="timestampsMultipleTimelines.u1.p1.s1.w9.ae" | ||
| interval="100660.0" | ||
| since="#timestampsMultipleTimelines.audio2.origin"/> | ||
| <when xml:id="timestampsMultipleTimelines.u1.p1.s1.w11.ab" | ||
| interval="100700.0" | ||
| since="#timestampsMultipleTimelines.audio2.origin"/> | ||
| <when xml:id="timestampsMultipleTimelines.u1.p1.s1.w11.ae" | ||
| interval="100730.0" | ||
| since="#timestampsMultipleTimelines.audio2.origin"/> | ||
| <when xml:id="timestampsMultipleTimelines.u1.p1.s1.w12.ab" | ||
| interval="100750.0" | ||
| since="#timestampsMultipleTimelines.audio2.origin"/> | ||
| <when xml:id="timestampsMultipleTimelines.u1.p1.s1.w12.ae" | ||
| interval="100770.0" | ||
| since="#timestampsMultipleTimelines.audio2.origin"/> | ||
| <when xml:id="timestampsMultipleTimelines.u1.p1.s1.w13.ab" | ||
| interval="100780.0" | ||
| since="#timestampsMultipleTimelines.audio2.origin"/> | ||
| <when xml:id="timestampsMultipleTimelines.u1.p1.s1.w13.ae" | ||
| interval="100850.0" | ||
| since="#timestampsMultipleTimelines.audio2.origin"/> | ||
| <when xml:id="timestampsMultipleTimelines.u1.p1.s1.w14.ab" | ||
| interval="100900.0" | ||
| since="#timestampsMultipleTimelines.audio2.origin"/> | ||
| <when xml:id="timestampsMultipleTimelines.u1.p1.s1.w14.ae" | ||
| interval="100960.0" | ||
| since="#timestampsMultipleTimelines.audio2.origin"/> | ||
| <when xml:id="timestampsMultipleTimelines.u1.p1.s1.w15.ab" | ||
| interval="101000.0" | ||
| since="#timestampsMultipleTimelines.audio2.origin"/> | ||
| <when xml:id="timestampsMultipleTimelines.u1.p1.s1.w15.ae" | ||
| interval="101040.0" | ||
| since="#timestampsMultipleTimelines.audio2.origin"/> | ||
| </timeline> | ||
| </body> | ||
| </text> | ||
| </TEI> |
Oops, something went wrong.