[add] github workflow

.github/workflows/ci.yaml

@@ -0,0 +1,30 @@
+name: Run BaseX Tests
+
+on:
+  pull_request:
+    branches:
+      - main
+  workflow_dispatch: # Enables manual trigger
+  
+jobs:
+  test:
+    runs-on: ubuntu-latest
+
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v2
+
+    - name: Set up Java
+      uses: actions/setup-java@v2
+      with:
+        java-version: '11'
+        distribution: 'temurin
+
+    - name: Install BaseX
+      run: |
+        wget http://files.basex.org/releases/10.7/BaseX107.zip
+        unzip BaseX107.zip -d basex
+
+    - name: Run BaseX Tests
+      run: |
+        ./basex/bin/basex -t .

package.json

@@ -7,7 +7,7 @@
     "doc": "docs"
   },
   "scripts": {
-    "test": "basex -t ."
+    "test": "%BASEX10%/bin/basex -t ."
   },
   "keywords": [
     "pdf",

samples.pdf/readme.md

@@ -4,4 +4,5 @@
 * [BaseX100.pdf](https://files.basex.org/releases/10.0/BaseX100.pdf)
 * [icelandic-dictionary.pdf](http://css4.pub/2015/icelandic/dictionary.pdf)
 * [page-numbers.pdf](https://www.w3.org/WAI/WCAG22/working-examples/pdf-page-numbers/page-numbers).
-* [Sentience-in-Cephalopod-Molluscs-and-Decapod-Crustaceans](https://www.lse.ac.uk/News/News-Assets/PDFs/2021/Sentience-in-Cephalopod-Molluscs-and-Decapod-Crustaceans-Final-Report-November-2021.pdfpdf)
+* [Sentience-in-Cephalopod-Molluscs-and-Decapod-Crustaceans](https://www.lse.ac.uk/News/News-Assets/PDFs/2021/Sentience-in-Cephalopod-Molluscs-and-Decapod-Crustaceans-Final-Report-November-2021.pdf)
+* [Legal RAG Hallucinations](https://law.stanford.edu/wp-content/uploads/2024/05/Legal_RAG_Hallucinations.pdf)

src/lib/pdfscrape.xqm

@@ -35,7 +35,7 @@ as element(page){
   return <page index="{ $page }">{ $found, $line1 }</page>
 };
 
-(:~ empty or attributes created by matching $style with $line1 :)
+(:~ attributes created by matching $style with $line1  or empty :)
 declare function pdfscrape:line-report($style as xs:string, $line1 as xs:string)
 as attribute(*)*{
     if(matches($line1,$pdfscrape:pats?($style)))
@@ -52,10 +52,12 @@ as map(*) {
   $pages[@number]!map:entry(string(@number),string(@index))
   =>map:merge(map{"duplicates":"combine"})
 };
+
 (:~ %match 
 $l page labels
 :)
-declare function pdfscrape:score($l as xs:string*,$report as element(page)*)  
+declare function pdfscrape:score($l as xs:string*,
+                                 $report as element(page)*)  
 { 
   let $s:=$report!(if(@number)then string(@number) else "")
  let $match:= for-each-pair($l,$s,function($l,$s){if($s eq "")then 0 else if ($s eq $l)then 1 else -1})
@@ -76,3 +78,7 @@ as xs:integer{
     => array:head() 
 };
 
+declare function pdfscrape:characters($str as xs:string)
+{
+
+};

src/scratch/pdfbox.xq

@@ -19,6 +19,5 @@ $samples?world=>file:resolve-path($base)
 
 
 
-let $doc:=pdfbox:open($PDF)
 
-return pdfbox:information($doc)
+ pdfbox:report($PDF)