Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
A
any2txt
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Wiki
Redmine
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Build
Pipelines
Jobs
Pipeline schedules
Artifacts
Deploy
Releases
Container registry
Model registry
Operate
Environments
Monitor
Incidents
Analyze
Value stream analytics
Contributor analytics
CI/CD analytics
Repository analytics
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
GitLab community forum
Contribute to GitLab
Provide feedback
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
nlpworkers
any2txt
Commits
898b0a7e
Commit
898b0a7e
authored
Jul 6, 2023
by
Paweł Walkowiak
Browse files
Options
Downloads
Patches
Plain Diff
Restore version
parent
30426ab1
Branches
Branches containing commit
No related tags found
Loading
Pipeline
#11509
passed
Jul 6, 2023
Stage: build_develop
Changes
1
Pipelines
1
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
module/src/main/java/pl/clarin/any2txt/Converter.java
+29
-30
29 additions, 30 deletions
module/src/main/java/pl/clarin/any2txt/Converter.java
with
29 additions
and
30 deletions
module/src/main/java/pl/clarin/any2txt/Converter.java
+
29
−
30
View file @
898b0a7e
...
@@ -89,42 +89,41 @@ public class Converter extends Worker {
...
@@ -89,42 +89,41 @@ public class Converter extends Worker {
if
(
"application/x-msdownload"
.
equals
(
tika
.
detect
(
inS
))){
if
(
"application/x-msdownload"
.
equals
(
tika
.
detect
(
inS
))){
tika
=
new
Tika
(
new
TextDetector
());
tika
=
new
Tika
(
new
TextDetector
());
}
}
if
(
"text/plain"
.
equals
(
tika
.
detect
(
inS
))){
// if("text/plain".equals(tika.detect(inS))){
try
{
// try {
DocumentBuilderFactory
factory
=
DocumentBuilderFactory
.
newInstance
();
// DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
DocumentBuilder
loader
=
factory
.
newDocumentBuilder
();
// DocumentBuilder loader = factory.newDocumentBuilder();
inS
.
setEncoding
(
"UTF-8"
);
// Document document = loader.parse(inS);
Document
document
=
loader
.
parse
(
inS
);
//
// DocumentTraversal trav = (DocumentTraversal) document;
DocumentTraversal
trav
=
(
DocumentTraversal
)
document
;
// NodeIterator iterator = trav.createNodeIterator(document.getDocumentElement(),
NodeIterator
iterator
=
trav
.
createNodeIterator
(
document
.
getDocumentElement
(),
// NodeFilter.SHOW_ELEMENT, null, true);
NodeFilter
.
SHOW_ELEMENT
,
null
,
true
);
//
// for (Node n = iterator.nextNode(); n != null; n = iterator.nextNode()) {
for
(
Node
n
=
iterator
.
nextNode
();
n
!=
null
;
n
=
iterator
.
nextNode
())
{
//
// String text = n.getTextContent().trim();
String
text
=
n
.
getTextContent
().
trim
();
//
// if (!text.isEmpty()) {
if
(!
text
.
isEmpty
())
{
// System.out.println(text);
System
.
out
.
println
(
text
);
// }
}
// }
}
// BodyContentHandler handler = new BodyContentHandler();
// BodyContentHandler handler = new BodyContentHandler();
// ParseContext pcontext = new ParseContext();
// ParseContext pcontext = new ParseContext();
// XMLParser xmlparser = new XMLParser();
// XMLParser xmlparser = new XMLParser();
// xmlparser.parse(inS, handler, metadata, pcontext);
// xmlparser.parse(inS, handler, metadata, pcontext);
// System.out.println("Contents of the document:" + handler.toString());
// System.out.println("Contents of the document:" + handler.toString());
}
catch
(
SAXException
ex
)
{
//
} catch (SAXException ex) {
Logger
.
getLogger
(
Converter
.
class
.
getName
()).
log
(
Level
.
WARNING
,
"Problems in xml processing "
+
ex
.
getMessage
(),
ex
.
getMessage
());
//
Logger.getLogger(Converter.class.getName()).log(Level.WARNING, "Problems in xml processing " + ex.getMessage(), ex.getMessage());
tika
=
new
Tika
(
new
TextDetector
());
//
tika = new Tika(new TextDetector());
}
catch
(
ParserConfigurationException
ex
)
{
//
} catch (ParserConfigurationException ex) {
Logger
.
getLogger
(
Converter
.
class
.
getName
()).
log
(
Level
.
WARNING
,
"Problems in xml processing "
+
ex
.
getMessage
(),
ex
.
getMessage
());
//
Logger.getLogger(Converter.class.getName()).log(Level.WARNING, "Problems in xml processing " + ex.getMessage(), ex.getMessage());
tika
=
new
Tika
(
new
TextDetector
());
//
tika = new Tika(new TextDetector());
}
catch
(
IOException
ex
)
{
//
} catch (IOException ex) {
Logger
.
getLogger
(
Converter
.
class
.
getName
()).
log
(
Level
.
WARNING
,
"Problems in xml processing "
+
ex
.
getMessage
(),
ex
.
getMessage
());
//
Logger.getLogger(Converter.class.getName()).log(Level.WARNING, "Problems in xml processing " + ex.getMessage(), ex.getMessage());
tika
=
new
Tika
(
new
TextDetector
());
//
tika = new Tika(new TextDetector());
}
//
}
}
//
}
tika
.
setMaxStringLength
(
maxLength
);
tika
.
setMaxStringLength
(
maxLength
);
String
txt
=
tika
.
parseToString
(
inS
,
metadata
);
String
txt
=
tika
.
parseToString
(
inS
,
metadata
);
...
...
This diff is collapsed.
Click to expand it.
Preview
0%
Loading
Try again
or
attach a new file
.
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Save comment
Cancel
Please
register
or
sign in
to comment