[
https://issues.apache.org/jira/browse/TIKA-4277?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17865297#comment-17865297
]
Tilman Hausherr commented on TIKA-4277:
---------------------------------------
To see what parameters are available and how to use them, do this:
{noformat}
java -jar tika-app-VERSION.jar --config=config.xml --dump-current-config
{noformat}
I get this:
{code:xml}
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<properties>
<!--for example: <mimeTypeRepository
resource="/org/apache/tika/mime/tika-mimetypes.xml"/>-->
<service-loader dynamic="true" loadErrorHandler="IGNORE"/>
<encodingDetectors>
<encodingDetector class="org.apache.tika.detect.DefaultEncodingDetector"/>
</encodingDetectors>
<translator class="org.apache.tika.language.translate.DefaultTranslator"/>
<detectors>
<detector class="org.apache.tika.detect.DefaultDetector"/>
</detectors>
<parsers>
<parser class="org.apache.tika.parser.DefaultParser"/>
<parser class="org.apache.tika.parser.pdf.PDFParser">
<params>
<param name="allowExtractionForAccessibility" type="bool">true</param>
<param name="averageCharTolerance" type="float">0.3</param>
<param name="catchIntermediateExceptions" type="bool">true</param>
<param name="detectAngles" type="bool">true</param>
<param name="dropThreshold" type="float">2.5</param>
<param name="enableAutoSpace" type="bool">true</param>
<param name="extractAcroFormContent" type="bool">true</param>
<param name="extractActions" type="bool">false</param>
<param name="extractAnnotationText" type="bool">true</param>
<param name="extractBookmarksText" type="bool">true</param>
<param name="extractFontNames" type="bool">false</param>
<param name="extractIncrementalUpdateInfo" type="bool">false</param>
<param name="extractInlineImageMetadataOnly" type="bool">false</param>
<param name="extractInlineImages" type="bool">false</param>
<param name="extractMarkedContent" type="bool">false</param>
<param name="extractUniqueInlineImagesOnly" type="bool">true</param>
<param name="ifXFAExtractOnlyXFA" type="bool">false</param>
<param name="imageStrategy" type="string">NONE</param>
<param name="maxIncrementalUpdates" type="int">10</param>
<param name="maxMainMemoryBytes" type="long">536870912</param>
<param name="ocrDPI" type="int">300</param>
<param name="ocrImageFormatName" type="string">png</param>
<param name="ocrImageQuality" type="float">1.0</param>
<param name="ocrImageType" type="string">GRAY</param>
<param name="ocrRenderingStrategy" type="string">ALL</param>
<param name="ocrStrategy" type="string">AUTO</param>
<param name="ocrStrategyAuto" type="string">10,10</param>
<param name="parseIncrementalUpdates" type="bool">false</param>
<param name="setKCMS" type="bool">false</param>
<param name="sortByPosition" type="bool">true</param>
<param name="spacingTolerance" type="float">0.5</param>
<param name="suppressDuplicateOverlappingText" type="bool">false</param>
<param name="throwOnEncryptedPayload" type="bool">false</param>
</params>
<imageGraphicsEngineFactory
class="org.apache.tika.parser.pdf.image.ImageGraphicsEngineFactory"/>
</parser>
</parsers>
</properties>
{code}
> PDF parse issue for text rotated
> --------------------------------
>
> Key: TIKA-4277
> URL: https://issues.apache.org/jira/browse/TIKA-4277
> Project: Tika
> Issue Type: Bug
> Components: tika-app, tika-server
> Affects Versions: 3.0.0-BETA, 2.9.2
> Reporter: ragebear
> Priority: Major
> Attachments: OtherPDFReader.png, sample2.pdf
>
>
> the incorrect result parsed by Tika and Tika Server 2.9.2 and 3.0beta
> The attached PDF cannot be correctly parsed by Tika 2.9.2 and 3.0beta, in
> server version and the standalone.
> if the text is rotated 90. The parsed result will have a line break after
> each letter of word. It happened to symbol, English letters, and JCK
> characters.
> In the server version, curl -g -T "sample2.pdf"
> [http://localhost:889/tika]
> --header "Accept: text/plain"
> In the standalone version, java.exe -jar "C:\TikaSearch\tika-app-2.9.2.jar"
> --text
> Both of above, deliver the the incorrect result in the attached pdf.
> The output result is below
> i
> n
> s
> e
> r
> t
>
> t
> e
> x
> t
>
> p
> r
> o
> b
> l
> e
> m
> insert text problem
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
