mirror of
https://github.com/MarginaliaSearch/MarginaliaSearch.git
synced 2025-10-05 21:22:39 +02:00
c661ebb619
It's long surpassed the single-responsibility library it once was, and is as such out of place in its original location, and fits better among the function-type modules.
229 lines
11 KiB
Plaintext
229 lines
11 KiB
Plaintext
@import nu.marginalia.language.model.WordRep
|
|
@import nu.marginalia.language.model.DocumentSentence
|
|
@import nu.marginalia.language.model.LanguageDefinition
|
|
@import java.util.*
|
|
@import java.util.stream.IntStream
|
|
|
|
@param String textSample
|
|
@param LanguageDefinition language
|
|
@param List<DocumentSentence> sentences
|
|
@param Map<Long, String> tagColors
|
|
@param Collection<WordRep> tfIdfReps
|
|
@param Collection<WordRep> titleReps
|
|
@param Collection<WordRep> nameLikeReps
|
|
@param Collection<WordRep> subjectLikeReps
|
|
@param Collection<String> artifacts
|
|
|
|
|
|
<!DOCTYPE html>
|
|
<html lang="en">
|
|
<head>
|
|
<meta charset="UTF-8">
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
|
<title>NLP Debug Tool</title>
|
|
<script src="https://cdn.tailwindcss.com"></script>
|
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.4.0/css/all.min.css">
|
|
<style>
|
|
.sentence-boundary {
|
|
border-left: 3px solid #3b82f6;
|
|
}
|
|
ruby rt {
|
|
font-size: 0.65em;
|
|
color: #6b7280;
|
|
}
|
|
</style>
|
|
</head>
|
|
<body class="bg-gray-50 min-h-screen">
|
|
<div class="container mx-auto px-4 py-8 max-w-6xl">
|
|
<!-- Header -->
|
|
<div class="mb-8">
|
|
<h1 class="text-3xl font-bold text-gray-900 mb-2">
|
|
<i class="fas fa-microscope text-blue-600 mr-3"></i>
|
|
Language Processing Debug Tool
|
|
</h1>
|
|
<p class="text-gray-600">Inspect and debug text processing pipeline components</p>
|
|
</div>
|
|
|
|
<!-- Input Section -->
|
|
<div class="bg-white rounded-lg shadow-sm border border-gray-200 mb-6">
|
|
<form method="post">
|
|
<div class="p-4 border-b border-gray-200">
|
|
<h2 class="text-lg font-semibold text-gray-900 mb-3">
|
|
<i class="fas fa-edit text-green-600 mr-2"></i>
|
|
Input Text
|
|
</h2>
|
|
|
|
<textarea name="textSample"
|
|
class="w-full p-4 border border-gray-300 rounded-md focus:ring-2 focus:ring-blue-500 focus:border-blue-500 resize-none"
|
|
rows="4"
|
|
placeholder="Enter your text here to analyze...">${textSample}</textarea>
|
|
<div class="flex justify-between items-center mt-3">
|
|
<button class="px-4 py-2 bg-blue-600 text-white rounded-md hover:bg-blue-700 transition-colors">
|
|
<i class="fas fa-cog mr-2"></i>Analyze
|
|
</button>
|
|
</div>
|
|
</div>
|
|
</form>
|
|
</div>
|
|
|
|
<!-- Results Grid -->
|
|
<div class="space-y-6">
|
|
|
|
<!-- Sentence Breakdown with POS Tags -->
|
|
<div class="bg-white rounded-lg shadow-sm border border-gray-200">
|
|
<div class="p-4 border-b border-gray-200">
|
|
<h2 class="text-lg font-semibold text-gray-900">
|
|
<i class="fas fa-list-ol text-purple-600 mr-2"></i>
|
|
Sentence Breakdown & POS Tags
|
|
</h2>
|
|
@if (language != null)
|
|
<div class="text-sm text-gray-500 mt-1">Auto-detected: ${language.displayName()} (${language.isoCode()})</div>
|
|
@endif
|
|
</div>
|
|
@if (sentences != null)
|
|
@for (DocumentSentence sentence : sentences)
|
|
<div class="p-4 space-y-4">
|
|
<div class="sentence-boundary pl-4 py-4 rounded">
|
|
@for (int pos : IntStream.range(0, sentence.length()).toArray())
|
|
<ruby class="p-4">
|
|
@if (language.hasPosParsing())
|
|
<span class="text-xl font-serif ${tagColors.get(sentence.posTags[pos])}">
|
|
${sentence.wordsLowerCase[pos]}
|
|
</span>
|
|
<rt>
|
|
${language.decodePosTagName(sentence.posTags[pos])}
|
|
|
|
@if (sentence.isAllCaps(pos))
|
|
<i class="fa-solid fa-angles-up"></i>
|
|
@elseif (sentence.isCapitalized(pos))
|
|
<i class="fa-solid fa-arrow-up"></i>
|
|
@endif
|
|
</rt>
|
|
@else <!-- pos tags disabled -->
|
|
<span class="text-xl font-serif">
|
|
${sentence.wordsLowerCase[pos]}
|
|
</span>
|
|
<rt>
|
|
@if (sentence.isAllCaps(pos))
|
|
<i class="fa-solid fa-angles-up"></i>
|
|
@elseif (sentence.isCapitalized(pos))
|
|
<i class="fa-solid fa-arrow-up"></i>
|
|
@endif
|
|
</rt>
|
|
@endif
|
|
</ruby>
|
|
@if (sentence.isSeparatorComma(pos))
|
|
<i class="fa-regular fa-circle"></i>
|
|
@endif
|
|
@endfor
|
|
</div>
|
|
</div>
|
|
@endfor
|
|
@endif
|
|
</div>
|
|
|
|
<!-- Keywords & N-grams -->
|
|
<div class="bg-white rounded-lg shadow-sm border border-gray-200">
|
|
<div class="p-4 border-b border-gray-200">
|
|
<h2 class="text-lg font-semibold text-gray-900">
|
|
<i class="fas fa-key text-indigo-600 mr-2"></i>
|
|
Keywords & N-grams
|
|
</h2>
|
|
</div>
|
|
<div class="p-4">
|
|
<div class="grid grid-cols-1 md:grid-cols-3 gap-6">
|
|
<!-- Keywords -->
|
|
@if (tfIdfReps != null && !tfIdfReps.isEmpty())
|
|
<div>
|
|
<h3 class="text-sm font-semibold text-gray-700 mb-3 flex items-center">
|
|
<i class="fas fa-star text-yellow-500 mr-2"></i>
|
|
Keywords (TF-IDF)
|
|
</h3>
|
|
<div class="space-y-2">
|
|
@for (WordRep rep : tfIdfReps)
|
|
<div class="flex justify-between items-center p-2 bg-gray-50 rounded">
|
|
<span class="text-sm font-medium">${rep.word}</span>
|
|
@if (rep.length > 1)
|
|
<span class="text-xs text-gray-600 bg-yellow-100 px-2 py-1 rounded">${rep.length}</span>
|
|
@endif
|
|
</div>
|
|
@endfor
|
|
</div>
|
|
</div>
|
|
@endif
|
|
@if (nameLikeReps != null && !nameLikeReps.isEmpty())
|
|
<div>
|
|
<h3 class="text-sm font-semibold text-gray-700 mb-3 flex items-center">
|
|
<i class="fas fa-star text-yellow-500 mr-2"></i>
|
|
Name-Like
|
|
</h3>
|
|
<div class="space-y-2">
|
|
@for (WordRep rep : nameLikeReps)
|
|
<div class="flex justify-between items-center p-2 bg-gray-50 rounded">
|
|
<span class="text-sm font-medium">${rep.word}</span>
|
|
@if (rep.length > 1)
|
|
<span class="text-xs text-gray-600 bg-yellow-100 px-2 py-1 rounded">${rep.length}</span>
|
|
@endif
|
|
</div>
|
|
@endfor
|
|
</div>
|
|
</div>
|
|
@endif
|
|
@if (subjectLikeReps != null && !subjectLikeReps.isEmpty())
|
|
<div>
|
|
<h3 class="text-sm font-semibold text-gray-700 mb-3 flex items-center">
|
|
<i class="fas fa-star text-yellow-500 mr-2"></i>
|
|
Subject-Like
|
|
</h3>
|
|
<div class="space-y-2">
|
|
@for (WordRep rep : subjectLikeReps)
|
|
<div class="flex justify-between items-center p-2 bg-gray-50 rounded">
|
|
<span class="text-sm font-medium">${rep.word}</span>
|
|
@if (rep.length > 1)
|
|
<span class="text-xs text-gray-600 bg-yellow-100 px-2 py-1 rounded">${rep.length}</span>
|
|
@endif
|
|
</div>
|
|
@endfor
|
|
</div>
|
|
</div>
|
|
@endif
|
|
@if (titleReps != null && !titleReps.isEmpty())
|
|
<div>
|
|
<h3 class="text-sm font-semibold text-gray-700 mb-3 flex items-center">
|
|
<i class="fas fa-star text-yellow-500 mr-2"></i>
|
|
Title
|
|
</h3>
|
|
<div class="space-y-2">
|
|
@for (WordRep rep : titleReps)
|
|
<div class="flex justify-between items-center p-2 bg-gray-50 rounded">
|
|
<span class="text-sm font-medium">${rep.word}</span>
|
|
@if (rep.length > 1)
|
|
<span class="text-xs text-gray-600 bg-yellow-100 px-2 py-1 rounded">${rep.length}</span>
|
|
@endif
|
|
</div>
|
|
@endfor
|
|
</div>
|
|
</div>
|
|
@endif
|
|
@if (artifacts != null && !artifacts.isEmpty())
|
|
<div>
|
|
<h3 class="text-sm font-semibold text-gray-700 mb-3 flex items-center">
|
|
<i class="fas fa-star text-yellow-500 mr-2"></i>
|
|
Title
|
|
</h3>
|
|
<div class="space-y-2">
|
|
@for (String word : artifacts)
|
|
<div class="flex justify-between items-center p-2 bg-gray-50 rounded">
|
|
<span class="text-sm font-medium">${word}</span>
|
|
</div>
|
|
@endfor
|
|
</div>
|
|
</div>
|
|
@endif
|
|
</div>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
</body>
|
|
</html> |