Skip to content
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

Jump to bottom

[MAINTENANCE] Added format unit tests. #894

Merged
merged 8 commits into from
Oct 26, 2023
Merged

[MAINTENANCE] Added format unit tests. #894

Show file tree
Hide file tree
Changes from 7 commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
50fb96b
Added format unit tests.
haogatyp Jan 30, 2023
c0c8b86
Fix unused local variable.
haogatyp Jan 30, 2023
e4d4426
Skip test for class not implemented
oliver-stoehr Oct 25, 2023
27b2db1
Fix AudioVideoMDTest
oliver-stoehr Oct 25, 2023
c04d9d3
Fix ModsTest
oliver-stoehr Oct 25, 2023
a023482
Fix AltoTest
oliver-stoehr Oct 25, 2023
0488d7a
Fix code style
oliver-stoehr Oct 26, 2023
68e0099
Add license and fix typo
oliver-stoehr Oct 26, 2023
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
66 changes: 66 additions & 0 deletions Tests/Fixtures/Format/alto.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,66 @@
<?xml version="1.0" encoding="UTF-8"?>
<alto xsi:schemaLocation="http://www.loc.gov/standards/alto/ns-v2# http://www.loc.gov/standards/alto/alto-v2.0.xsd"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xmlns="http://www.loc.gov/standards/alto/ns-v2#">
<Description>
<MeasurementUnit>pixel</MeasurementUnit>
<OCRProcessing ID="IdOcr">
<ocrProcessingStep>
<processingDateTime>2020-05-14</processingDateTime>
<processingSoftware>
<softwareCreator>ABBYY</softwareCreator>
<softwareName>ABBYY FineReader Engine</softwareName>
<softwareVersion>12</softwareVersion>
</processingSoftware>
</ocrProcessingStep>
</OCRProcessing>
</Description>
<Styles> </Styles>
<Layout>
<Page ID="Page1" PHYSICAL_IMG_NR="1" HEIGHT="2546" WIDTH="1801">
<PrintSpace HEIGHT="2546" WIDTH="1801" VPOS="0" HPOS="0">
<Illustration ID="Page1_Block1" HEIGHT="2546" WIDTH="1801" VPOS="0" HPOS="0"/>
<TextBlock ID="Page1_Block2" HEIGHT="241" WIDTH="1064" VPOS="2068" HPOS="470" language="de">
<Shape>
<Polygon POINTS="1506,2068 1533,2068 1533,2283 1534,2283 1534,2306 1509,2306 1509,2307 1104,2307 1104,2308 700,2308 700,2309 471,2309 471,2286 470,2286 470,2071 697,2071 697,2070 1101,2070 1101,2069 1506,2069 1506,2068"/>
</Shape>
<TextLine HEIGHT="102" WIDTH="628" VPOS="2076" HPOS="477">
<String WC="0.79777777194976807" CONTENT="Bürgertum" HEIGHT="95" WIDTH="437" VPOS="2083" HPOS="477"/>
<SP WIDTH="34" VPOS="2107" HPOS="915"/>
<String WC="0.66333335638046265" CONTENT="und" HEIGHT="76" WIDTH="155" VPOS="2076" HPOS="950"/>
</TextLine>
<TextLine HEIGHT="104" WIDTH="1051" VPOS="2199" HPOS="477">
<String WC="0.83142858743667603" CONTENT="Bürgerlichkeit" HEIGHT="102" WIDTH="574" VPOS="2201" HPOS="477"/>
<SP WIDTH="32" VPOS="2206" HPOS="1051"/>
<String WC="1." CONTENT="in" HEIGHT="68" WIDTH="74" VPOS="2205" HPOS="1084"/>
<SP WIDTH="34" VPOS="2204" HPOS="1159"/>
<String WC="0.8028571605682373" CONTENT="Dresden" HEIGHT="75" WIDTH="333" VPOS="2199" HPOS="1194"/>
</TextLine>
</TextBlock>
<TextBlock ID="Page1_Block3" HEIGHT="290" WIDTH="775" VPOS="307" HPOS="466" language="de">
<Shape>
<Polygon POINTS="1101,307 1241,307 1241,595 1104,595 1104,596 700,596 700,597 466,597 466,309 697,309 697,308 1101,308 1101,307"/>
</Shape>
<TextLine HEIGHT="98" WIDTH="752" VPOS="315" HPOS="473">
<String WC="0.75625002384185791" CONTENT="DRESDNER" HEIGHT="98" WIDTH="752" VPOS="315" HPOS="473"/>
</TextLine>
<TextLine HEIGHT="97" WIDTH="448" VPOS="492" HPOS="473">
<String WC="0.70399999618530273" CONTENT="HEFTE" HEIGHT="97" WIDTH="448" VPOS="492" HPOS="473"/>
</TextLine>
</TextBlock>
<GraphicalElement ID="Page1_Block4" HEIGHT="14" WIDTH="1674" VPOS="266" HPOS="55"/>
<GraphicalElement ID="Page1_Block5" HEIGHT="15" WIDTH="1674" VPOS="442" HPOS="55"/>
<GraphicalElement ID="Page1_Block6" HEIGHT="30" WIDTH="629" VPOS="680" HPOS="477"/>
<GraphicalElement ID="Page1_Block7" HEIGHT="8" WIDTH="170" VPOS="1963" HPOS="635"/>
<GraphicalElement ID="Page1_Block8" HEIGHT="141" WIDTH="11" VPOS="1019" HPOS="1197"/>
<GraphicalElement ID="Page1_Block9" HEIGHT="168" WIDTH="12" VPOS="948" HPOS="1411"/>
<Illustration ID="Page1_Block10" HEIGHT="175" WIDTH="88" VPOS="1469" HPOS="544">
<Shape>
<Polygon POINTS="544,1469 631,1469 631,1474 632,1474 632,1644 545,1644 545,1477 544,1477 544,1469"/>
</Shape>
</Illustration>
<Illustration ID="Page1_Block11" HEIGHT="207" WIDTH="61" VPOS="1657" HPOS="790"/>
</PrintSpace>
</Page>
</Layout>
</alto>
59 changes: 59 additions & 0 deletions Tests/Fixtures/Format/altoNoString.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,59 @@
<?xml version="1.0" encoding="UTF-8"?>
<alto xsi:schemaLocation="http://www.loc.gov/standards/alto/ns-v2# http://www.loc.gov/standards/alto/alto-v2.0.xsd"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xmlns="http://www.loc.gov/standards/alto/ns-v2#">
<Description>
<MeasurementUnit>pixel</MeasurementUnit>
<OCRProcessing ID="IdOcr">
<ocrProcessingStep>
<processingDateTime>2020-05-14</processingDateTime>
<processingSoftware>
<softwareCreator>ABBYY</softwareCreator>
<softwareName>ABBYY FineReader Engine</softwareName>
<softwareVersion>12</softwareVersion>
</processingSoftware>
</ocrProcessingStep>
</OCRProcessing>
</Description>
<Styles> </Styles>
<Layout>
<Page ID="Page1" PHYSICAL_IMG_NR="1" HEIGHT="2546" WIDTH="1801">
<PrintSpace HEIGHT="2546" WIDTH="1801" VPOS="0" HPOS="0">
<Illustration ID="Page1_Block1" HEIGHT="2546" WIDTH="1801" VPOS="0" HPOS="0"/>
<TextBlock ID="Page1_Block2" HEIGHT="241" WIDTH="1064" VPOS="2068" HPOS="470" language="de">
<Shape>
<Polygon POINTS="1506,2068 1533,2068 1533,2283 1534,2283 1534,2306 1509,2306 1509,2307 1104,2307 1104,2308 700,2308 700,2309 471,2309 471,2286 470,2286 470,2071 697,2071 697,2070 1101,2070 1101,2069 1506,2069 1506,2068"/>
</Shape>
<TextLine HEIGHT="102" WIDTH="628" VPOS="2076" HPOS="477">
<SP WIDTH="34" VPOS="2107" HPOS="915"/>
</TextLine>
<TextLine HEIGHT="104" WIDTH="1051" VPOS="2199" HPOS="477">
<SP WIDTH="32" VPOS="2206" HPOS="1051"/>
<SP WIDTH="34" VPOS="2204" HPOS="1159"/>
</TextLine>
</TextBlock>
<TextBlock ID="Page1_Block3" HEIGHT="290" WIDTH="775" VPOS="307" HPOS="466" language="de">
<Shape>
<Polygon POINTS="1101,307 1241,307 1241,595 1104,595 1104,596 700,596 700,597 466,597 466,309 697,309 697,308 1101,308 1101,307"/>
</Shape>
<TextLine HEIGHT="98" WIDTH="752" VPOS="315" HPOS="473">
</TextLine>
<TextLine HEIGHT="97" WIDTH="448" VPOS="492" HPOS="473">
</TextLine>
</TextBlock>
<GraphicalElement ID="Page1_Block4" HEIGHT="14" WIDTH="1674" VPOS="266" HPOS="55"/>
<GraphicalElement ID="Page1_Block5" HEIGHT="15" WIDTH="1674" VPOS="442" HPOS="55"/>
<GraphicalElement ID="Page1_Block6" HEIGHT="30" WIDTH="629" VPOS="680" HPOS="477"/>
<GraphicalElement ID="Page1_Block7" HEIGHT="8" WIDTH="170" VPOS="1963" HPOS="635"/>
<GraphicalElement ID="Page1_Block8" HEIGHT="141" WIDTH="11" VPOS="1019" HPOS="1197"/>
<GraphicalElement ID="Page1_Block9" HEIGHT="168" WIDTH="12" VPOS="948" HPOS="1411"/>
<Illustration ID="Page1_Block10" HEIGHT="175" WIDTH="88" VPOS="1469" HPOS="544">
<Shape>
<Polygon POINTS="544,1469 631,1469 631,1474 632,1474 632,1644 545,1644 545,1477 544,1477 544,1469"/>
</Shape>
</Illustration>
<Illustration ID="Page1_Block11" HEIGHT="207" WIDTH="61" VPOS="1657" HPOS="790"/>
</PrintSpace>
</Page>
</Layout>
</alto>
38 changes: 38 additions & 0 deletions Tests/Fixtures/Format/altoNoTextBlock.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,38 @@
<?xml version="1.0" encoding="UTF-8"?>
<alto xsi:schemaLocation="http://www.loc.gov/standards/alto/ns-v2# http://www.loc.gov/standards/alto/alto-v2.0.xsd"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xmlns="http://www.loc.gov/standards/alto/ns-v2#">
<Description>
<MeasurementUnit>pixel</MeasurementUnit>
<OCRProcessing ID="IdOcr">
<ocrProcessingStep>
<processingDateTime>2020-05-14</processingDateTime>
<processingSoftware>
<softwareCreator>ABBYY</softwareCreator>
<softwareName>ABBYY FineReader Engine</softwareName>
<softwareVersion>12</softwareVersion>
</processingSoftware>
</ocrProcessingStep>
</OCRProcessing>
</Description>
<Styles> </Styles>
<Layout>
<Page ID="Page1" PHYSICAL_IMG_NR="1" HEIGHT="2546" WIDTH="1801">
<PrintSpace HEIGHT="2546" WIDTH="1801" VPOS="0" HPOS="0">
<Illustration ID="Page1_Block1" HEIGHT="2546" WIDTH="1801" VPOS="0" HPOS="0"/>
<GraphicalElement ID="Page1_Block4" HEIGHT="14" WIDTH="1674" VPOS="266" HPOS="55"/>
<GraphicalElement ID="Page1_Block5" HEIGHT="15" WIDTH="1674" VPOS="442" HPOS="55"/>
<GraphicalElement ID="Page1_Block6" HEIGHT="30" WIDTH="629" VPOS="680" HPOS="477"/>
<GraphicalElement ID="Page1_Block7" HEIGHT="8" WIDTH="170" VPOS="1963" HPOS="635"/>
<GraphicalElement ID="Page1_Block8" HEIGHT="141" WIDTH="11" VPOS="1019" HPOS="1197"/>
<GraphicalElement ID="Page1_Block9" HEIGHT="168" WIDTH="12" VPOS="948" HPOS="1411"/>
<Illustration ID="Page1_Block10" HEIGHT="175" WIDTH="88" VPOS="1469" HPOS="544">
<Shape>
<Polygon POINTS="544,1469 631,1469 631,1474 632,1474 632,1644 545,1644 545,1477 544,1477 544,1469"/>
</Shape>
</Illustration>
<Illustration ID="Page1_Block11" HEIGHT="207" WIDTH="61" VPOS="1657" HPOS="790"/>
</PrintSpace>
</Page>
</Layout>
</alto>
48 changes: 48 additions & 0 deletions Tests/Fixtures/Format/altoNoTextLine.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,48 @@
<?xml version="1.0" encoding="UTF-8"?>
<alto xsi:schemaLocation="http://www.loc.gov/standards/alto/ns-v2# http://www.loc.gov/standards/alto/alto-v2.0.xsd"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xmlns="http://www.loc.gov/standards/alto/ns-v2#">
<Description>
<MeasurementUnit>pixel</MeasurementUnit>
<OCRProcessing ID="IdOcr">
<ocrProcessingStep>
<processingDateTime>2020-05-14</processingDateTime>
<processingSoftware>
<softwareCreator>ABBYY</softwareCreator>
<softwareName>ABBYY FineReader Engine</softwareName>
<softwareVersion>12</softwareVersion>
</processingSoftware>
</ocrProcessingStep>
</OCRProcessing>
</Description>
<Styles> </Styles>
<Layout>
<Page ID="Page1" PHYSICAL_IMG_NR="1" HEIGHT="2546" WIDTH="1801">
<PrintSpace HEIGHT="2546" WIDTH="1801" VPOS="0" HPOS="0">
<Illustration ID="Page1_Block1" HEIGHT="2546" WIDTH="1801" VPOS="0" HPOS="0"/>
<TextBlock ID="Page1_Block2" HEIGHT="241" WIDTH="1064" VPOS="2068" HPOS="470" language="de">
<Shape>
<Polygon POINTS="1506,2068 1533,2068 1533,2283 1534,2283 1534,2306 1509,2306 1509,2307 1104,2307 1104,2308 700,2308 700,2309 471,2309 471,2286 470,2286 470,2071 697,2071 697,2070 1101,2070 1101,2069 1506,2069 1506,2068"/>
</Shape>
</TextBlock>
<TextBlock ID="Page1_Block3" HEIGHT="290" WIDTH="775" VPOS="307" HPOS="466" language="de">
<Shape>
<Polygon POINTS="1101,307 1241,307 1241,595 1104,595 1104,596 700,596 700,597 466,597 466,309 697,309 697,308 1101,308 1101,307"/>
</Shape>
</TextBlock>
<GraphicalElement ID="Page1_Block4" HEIGHT="14" WIDTH="1674" VPOS="266" HPOS="55"/>
<GraphicalElement ID="Page1_Block5" HEIGHT="15" WIDTH="1674" VPOS="442" HPOS="55"/>
<GraphicalElement ID="Page1_Block6" HEIGHT="30" WIDTH="629" VPOS="680" HPOS="477"/>
<GraphicalElement ID="Page1_Block7" HEIGHT="8" WIDTH="170" VPOS="1963" HPOS="635"/>
<GraphicalElement ID="Page1_Block8" HEIGHT="141" WIDTH="11" VPOS="1019" HPOS="1197"/>
<GraphicalElement ID="Page1_Block9" HEIGHT="168" WIDTH="12" VPOS="948" HPOS="1411"/>
<Illustration ID="Page1_Block10" HEIGHT="175" WIDTH="88" VPOS="1469" HPOS="544">
<Shape>
<Polygon POINTS="544,1469 631,1469 631,1474 632,1474 632,1644 545,1644 545,1477 544,1477 544,1469"/>
</Shape>
</Illustration>
<Illustration ID="Page1_Block11" HEIGHT="207" WIDTH="61" VPOS="1657" HPOS="790"/>
</PrintSpace>
</Page>
</Layout>
</alto>
36 changes: 36 additions & 0 deletions Tests/Fixtures/Format/audioVideo.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,36 @@
<?xml version="1.0" encoding="UTF-8"?>
<mets:mets xmlns:mets="http://www.loc.gov/METS/"
xmlns:mods="http://www.loc.gov/mods/v3"
xmlns:videomd="http://www.loc.gov/videoMD/"
xmlns:audiomd="http://www.loc.gov/audioMD/"
xmlns:dv="http://dfg-viewer.de/"
xmlns:xlink="http://www.w3.org/1999/xlink"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://www.loc.gov/METS/ http://www.loc.gov/standards/mets/mets.xsd http://www.loc.gov/mods/v3 http://www.loc.gov/standards/mods/mods.xsd http://www.loc.gov/videoMD/ https://www.loc.gov/standards/amdvmd/videoMD.xsd">
<mets:amdSec ID="AMD">
<mets:mdWrap MDTYPE="OTHER" MIMETYPE="text/xml" OTHERMDTYPE="VIDEOMD">
<mets:xmlData>
<videomd:fileData>
<videomd:color>Color</videomd:color>
<videomd:compression>
<videomd:codecCreatorApp>Phoenix Finish</videomd:codecCreatorApp>
<videomd:codecName>Apple ProRes 4444</videomd:codecName>
</videomd:compression>
<videomd:frameRate mode="Fixed">24</videomd:frameRate>
<videomd:sound>Yes</videomd:sound>
</videomd:fileData>
<videomd:videoInfo>
<videomd:aspectRatio>1.375:1</videomd:aspectRatio>
<videomd:dimensions LENGTH="1808" UNITS="frames" />
<videomd:duration>00:01:30.07</videomd:duration>
<videomd:frame>
<videomd:frameRate>24</videomd:frameRate>
</videomd:frame>
</videomd:videoInfo>
<audiomd:audioInfo>
<audiomd:duration>01:10:35.08</audiomd:duration>
</audiomd:audioInfo>
</mets:xmlData>
</mets:mdWrap>
</mets:amdSec>
</mets:mets>
Loading