1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
|
"use client";
import React, { useMemo } from "react";
import { GranularityId } from "./LevelPicker";
import { NLP } from "sortug-ai";
type AnalysisEngine = "spacy" | "stanza";
interface Paragraph {
id: string;
text: string;
start_char: number;
end_char: number;
sentences: NLP.Spacy.Sentence[];
}
const segmentByParagraphs = (
inputText: string,
allSentences: NLP.Spacy.Sentence[],
): Paragraph[] => {
const paragraphs: Paragraph[] = [];
const paraTexts = inputText.split(/\n\n+/);
let currentDocCharOffset = 0;
let sentenceIdx = 0;
paraTexts.forEach((paraText, idx) => {
const paraStartChar = currentDocCharOffset;
const paraEndChar = paraStartChar + paraText.length;
const paraSentences: NLP.Spacy.Sentence[] = [];
while (sentenceIdx < allSentences.length) {
const sent = allSentences[sentenceIdx]!;
if (sent.start < paraEndChar) {
paraSentences.push(sent);
sentenceIdx++;
} else {
break;
}
}
paragraphs.push({
id: `para-${idx}`,
text: paraText,
start_char: paraStartChar,
end_char: paraEndChar,
sentences: paraSentences,
});
currentDocCharOffset =
paraEndChar +
(inputText.substring(paraEndChar).match(/^\n\n+/)?.[0].length || 0);
});
return paragraphs;
};
// --- Text Viewer ---
interface TextViewerProps {
nlpData: NLP.Spacy.SpacyRes;
engine: AnalysisEngine;
granularity: GranularityId;
onElementSelect: (
elementType: GranularityId,
elementData: any,
fullText: string,
) => void;
}
const TextViewer: React.FC<TextViewerProps> = ({
nlpData,
engine,
granularity,
onElementSelect,
}) => {
const paragraphs = useMemo(
() => segmentByParagraphs(nlpData.input, nlpData.segments),
[nlpData],
);
const getElementText = (element: any, fullInput: string): string => {
if (element.text) return element.text; // Already has text
if ("start_char" in element && "end_char" in element) {
// Stanza word/token/sentence/entity
return fullInput.substring(element.start_char, element.end_char);
}
if ("start" in element && "end" in element) {
// spaCy token/sentence/entity
return fullInput.substring(element.start, element.end);
}
return "N/A";
};
const renderInteractiveSpan = (
key: string | number,
text: string,
data: any,
type: GranularityId,
baseClasses: string = "",
hoverClasses: string = "hover:bg-yellow-200",
) => (
<span
key={key}
className={`cursor-pointer transition-colors duration-150 ${baseClasses} ${hoverClasses} p-0.5 rounded`}
onClick={(e) => {
e.stopPropagation(); // Prevent clicks bubbling to parent elements
onElementSelect(type, data, getElementText(data, nlpData.input));
}}
>
{text}
</span>
);
return (
<div className="text-lg text-gray-800 leading-relaxed bg-white p-4 sm:p-6 rounded-xl shadow-inner">
{granularity === "text"
? renderInteractiveSpan(
"full-text",
nlpData.input,
nlpData,
"text",
"block",
"hover:bg-sky-100",
)
: paragraphs.map((para) => (
<div
key={para.id}
className={`mb-4 ${granularity === "paragraph" ? "p-2 rounded-md shadow-sm bg-gray-50" : ""}`}
onClick={
granularity === "paragraph"
? (e) => {
e.stopPropagation();
onElementSelect("paragraph", para, para.text);
}
: undefined
}
style={granularity === "paragraph" ? { cursor: "pointer" } : {}}
>
{para.sentences.map((sent, sentIdx) => {
const sentenceText = getElementText(sent, nlpData.input);
const sentenceKey = `sent-${para.id}-${sentIdx}`;
if (granularity === "sentence" || granularity === "clause") {
return renderInteractiveSpan(
sentenceKey,
sentenceText,
sent,
granularity,
"mr-1 inline-block bg-gray-100 shadow-xs",
"hover:bg-sky-200",
);
} else if (
granularity === "word" ||
granularity === "syllable" ||
granularity === "phoneme"
) {
let currentWordRenderIndex = 0; // to add spaces correctly
return (
<span key={sentenceKey} className="mr-1">
{" "}
{/* Sentence wrapper */}
{sent.words.map((word, idx) => {
const wordText = getElementText(word, nlpData.input);
const wordKey = `${sentenceKey}-tok-${idx}-word-${word}`;
const space = currentWordRenderIndex > 0 ? " " : "";
currentWordRenderIndex++;
return (
<React.Fragment key={wordKey}>
{space}
{renderInteractiveSpan(
wordKey,
wordText,
word,
granularity,
"bg-gray-50",
"hover:bg-yellow-300",
)}
</React.Fragment>
);
})}
</span>
);
}
// Fallback for paragraph view if no other granularity matches (should not happen if logic is correct)
return (
<span key={sentenceKey} className="mr-1">
{sentenceText}
</span>
);
})}
</div>
))}
</div>
);
};
export default TextViewer;
|
