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

Fix fulltext block start #1203

Merged
merged 3 commits into from
Dec 26, 2024
Merged

Fix fulltext block start #1203

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
6c1e1e6
fix LINEBLOCKSTARTS for new generated files #712
lfoppiano Nov 21, 2024
6aeed31
Merge branch 'master' into elifesciencesfix-fulltext-block-start
lfoppiano Dec 26, 2024
671feb0
Fix merge
lfoppiano Dec 26, 2024
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
4 changes: 3 additions & 1 deletion grobid-core/src/main/java/org/grobid/core/engines/FullTextParser.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -852,6 +852,7 @@ else if (nbAuthorType > (bibDataSets.size() / 2))
}
}

boolean isFirstBlockToken = true;
while (n < lastPos) {
if (blockIndex == dp2.getBlockPtr()) {
//if (n > block.getEndToken()) {
Expand Down Expand Up @@ -969,7 +970,7 @@ else if (lineStartX - previousLineStartX > characterWidth)
features.alignmentStatus = "ALIGNEDLEFT";
}

if (n == 0) {
if (isFirstBlockToken) {
features.lineStatus = "LINESTART";
// be sure that previous token is closing a line, except if it's a starting line
if (previousFeatures != null) {
Expand Down Expand Up @@ -1146,6 +1147,7 @@ else if (features.blockStatus == null) {
mm += text.length();
nn += text.length();
previousFeatures = features;
isFirstBlockToken = false;
}
// lowest position of the block
lowestPos = block.getY() + block.getHeight();
Expand Down
84 changes: 70 additions & 14 deletions grobid-core/src/test/kotlin/org/grobid/core/engines/FullTextParserTest.kt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,9 +1,11 @@
package org.grobid.core.engines

import jnr.posix.BaseIovec.Layout
import org.apache.commons.lang3.StringUtils
import org.apache.commons.lang3.tuple.Triple
import org.grobid.core.analyzers.GrobidAnalyzer
import org.grobid.core.document.Document
import org.grobid.core.document.DocumentPiece
import org.grobid.core.document.DocumentPointer
import org.grobid.core.engines.label.TaggingLabels.TABLE_LABEL
import org.grobid.core.factory.GrobidFactory
import org.grobid.core.layout.LayoutToken
Expand All @@ -13,8 +15,8 @@ import org.grobid.core.utilities.GrobidProperties
import org.grobid.core.utilities.GrobidTestUtils
import org.hamcrest.CoreMatchers
import org.hamcrest.CoreMatchers.`is`
import org.hamcrest.MatcherAssert
import org.hamcrest.MatcherAssert.assertThat
import org.hamcrest.Matchers
import org.hamcrest.Matchers.hasSize
import org.hamcrest.collection.IsCollectionWithSize
import org.junit.AfterClass
Expand Down Expand Up @@ -88,8 +90,8 @@ class FullTextParserTest {
.map { l: String -> l.split("\t".toRegex()).dropLastWhile { it.isEmpty() }.toTypedArray()[0] }
.collect(Collectors.joining(" "))

MatcherAssert.assertThat(reconstructedText, CoreMatchers.`is`("FIG . 1 . λ ( T ) vs . T for YBCO"))
MatcherAssert.assertThat(
assertThat(reconstructedText, CoreMatchers.`is`("FIG . 1 . λ ( T ) vs . T for YBCO"))
assertThat(
tokenisation.split("\n".toRegex()).dropLastWhile { it.isEmpty() }.toTypedArray().size,
CoreMatchers.`is`(13)
)
Expand Down Expand Up @@ -134,10 +136,10 @@ class FullTextParserTest {
}
}

MatcherAssert.assertThat<List<String>>(output, IsCollectionWithSize.hasSize(2))
MatcherAssert.assertThat(output[0], CoreMatchers.`is`("FIG . 1 . λ ( T )"))
MatcherAssert.assertThat(output[1], CoreMatchers.`is`("vs . T for YBCO"))
MatcherAssert.assertThat(
assertThat<List<String>>(output, IsCollectionWithSize.hasSize(2))
assertThat(output[0], CoreMatchers.`is`("FIG . 1 . λ ( T )"))
assertThat(output[1], CoreMatchers.`is`("vs . T for YBCO"))
assertThat(
tokenisation.split("\n".toRegex()).dropLastWhile { it.isEmpty() }.toTypedArray().size,
CoreMatchers.`is`(15)
)
Expand Down Expand Up @@ -177,8 +179,8 @@ class FullTextParserTest {
.map { l: String -> l.split("\t".toRegex()).dropLastWhile { it.isEmpty() }.toTypedArray()[0] }
.collect(Collectors.joining(" "))

MatcherAssert.assertThat(reconstructedText, CoreMatchers.`is`("FIG . 1 . λ ( T ) vs . T for YBCO"))
MatcherAssert.assertThat(
assertThat(reconstructedText, CoreMatchers.`is`("FIG . 1 . λ ( T ) vs . T for YBCO"))
assertThat(
tokenisation.split("\n".toRegex()).dropLastWhile { it.isEmpty() }.toTypedArray().size,
CoreMatchers.`is`(13)
)
Expand Down Expand Up @@ -223,10 +225,10 @@ class FullTextParserTest {
}
}

MatcherAssert.assertThat<List<String>>(output, IsCollectionWithSize.hasSize(2))
MatcherAssert.assertThat(output[0], CoreMatchers.`is`("FIG . 1 . λ ( T )"))
MatcherAssert.assertThat(output[1], CoreMatchers.`is`("vs . T for YBCO"))
MatcherAssert.assertThat(
assertThat<List<String>>(output, IsCollectionWithSize.hasSize(2))
assertThat(output[0], CoreMatchers.`is`("FIG . 1 . λ ( T )"))
assertThat(output[1], CoreMatchers.`is`("vs . T for YBCO"))
assertThat(
tokenisation.split("\n".toRegex()).dropLastWhile { it.isEmpty() }.toTypedArray().size,
CoreMatchers.`is`(15)
)
Expand Down Expand Up @@ -382,4 +384,58 @@ class FullTextParserTest {

assertThat(consolidatedTable3ResultCandidateThroughSequence, `is`(67))
}

@Test
@Throws(Exception::class)
fun testShouldOutputBlockStartForRegularBlock() {
val blockText = "This is a block"
val doc = Document.createFromText(blockText)
val documentParts = getWholeDocumentParts(doc)
val dataAndTokens = FullTextParser.getBodyTextFeatured(doc, documentParts)
// LOGGER.debug("data debug: {}", dataAndTokens.getLeft());
val lines = dataAndTokens.left.split("\n".toRegex()).dropLastWhile { it.isEmpty() }.toTypedArray()
assertThat(
"lines[0] fields",
Arrays.asList(
*lines[0].split("\\s".toRegex())
.dropLastWhile { it.isEmpty() }
.toTypedArray()), `is`(Matchers.hasItem("BLOCKSTART"))
)
}

@Test
@Throws(Exception::class)
fun testShouldOutputBlockStartForBlockStartingWithLineFeed() {
val blockText = "\nThis is a block"
val doc = Document.createFromText(blockText)
assertThat(
"doc.block[0].tokens[0].text",
doc.blocks[0].getTokens()[0].text,
CoreMatchers.`is`("\n")
)
val documentParts = getWholeDocumentParts(doc)
val dataAndTokens = FullTextParser.getBodyTextFeatured(doc, documentParts)
// LOGGER.debug("data debug: {}", dataAndTokens.getLeft());
val lines = dataAndTokens.left.split("\n".toRegex()).dropLastWhile { it.isEmpty() }.toTypedArray()
assertThat(
"lines[0] fields",
Arrays.asList(*lines[0].split("\\s".toRegex()).dropLastWhile { it.isEmpty() }.toTypedArray()),
`is`(Matchers.hasItem("BLOCKSTART"))
)
}

private fun getWholeDocumentPiece(doc: Document): DocumentPiece {
return DocumentPiece(
DocumentPointer(0, 0, 0),
DocumentPointer(0, doc.tokenizations.size - 1, doc.tokenizations.size - 1)
)
}

private fun getWholeDocumentParts(doc: Document): SortedSet<DocumentPiece> {
return TreeSet(
setOf(
getWholeDocumentPiece(doc)
)
)
}
}
Loading