danvics/openreader
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Build fixes

Browse source
This commit is contained in:
Richard Roberson 2025-01-26 02:15:14 -07:00
parent 43d34fb2f7
commit 9374d3efbe
2 changed files with 82 additions and 82 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
src/app/pdf/[id]/page.tsx
View file

@ -4,7 +4,7 @@ import dynamic from 'next/dynamic';
import { usePDF } from '@/contexts/PDFContext';
import { useParams } from 'next/navigation';
import Link from 'next/link';
import { use, useCallback, useEffect, useState } from 'react';
import { useCallback, useEffect, useState } from 'react';
import { PDFSkeleton } from '@/components/PDFSkeleton';
import { useTTS } from '@/contexts/TTSContext';

162
src/contexts/PDFContext.tsx
View file

@ -148,89 +148,89 @@ export function PDFProvider({ children }: { children: ReactNode }) {
}
}, []);
function onDocumentLoadSuccess({ numPages }: { numPages: number }): void {
const onDocumentLoadSuccess = useCallback(({ numPages }: { numPages: number }) => {
console.log('Document loaded:', numPages);
setCurrDocPages(numPages);
}
}, []);
// Extract text from a PDF file
const extractTextFromPDF = useCallback(async (pdfURL: string, currDocPage: number): Promise<string> => {
try {
const base64Data = pdfURL.split(',')[1];
const binaryData = atob(base64Data);
const bytes = new Uint8Array(binaryData.length);
for (let i = 0; i < binaryData.length; i++) {
bytes[i] = binaryData.charCodeAt(i);
}
const loadingTask = pdfjs.getDocument({ data: bytes });
const pdf = await loadingTask.promise;
// Get only the specified page
const page = await pdf.getPage(currDocPage);
const textContent = await page.getTextContent();
// Filter out non-text items and assert proper type
const textItems = textContent.items.filter((item): item is TextItem =>
'str' in item && 'transform' in item
);
// Group text items into lines based on their vertical position
const tolerance = 2;
const lines: TextItem[][] = [];
let currentLine: TextItem[] = [];
let currentY: number | null = null;
textItems.forEach((item) => {
const y = item.transform[5];
if (currentY === null) {
currentY = y;
currentLine.push(item);
} else if (Math.abs(y - currentY) < tolerance) {
currentLine.push(item);
} else {
lines.push(currentLine);
currentLine = [item];
currentY = y;
}
});
lines.push(currentLine);
// Process each line to build text
let pageText = '';
for (const line of lines) {
// Sort items horizontally within the line
line.sort((a, b) => a.transform[4] - b.transform[4]);
let lineText = '';
let prevItem: TextItem | null = null;
for (const item of line) {
if (!prevItem) {
lineText = item.str;
} else {
const prevEndX = prevItem.transform[4] + (prevItem.width ?? 0);
const currentStartX = item.transform[4];
const space = currentStartX - prevEndX;
// Add space if gap is significant, otherwise concatenate directly
if (space > ((item.width ?? 0) * 0.3)) {
lineText += ' ' + item.str;
} else {
lineText += item.str;
}
}
prevItem = item;
}
pageText += lineText + ' ';
}
return pageText.replace(/\s+/g, ' ').trim();
} catch (error) {
console.error('Error extracting text from PDF:', error);
throw new Error('Failed to extract text from PDF');
const extractTextFromPDF = useCallback(async (pdfURL: string, currDocPage: number): Promise<string> => {
try {
const base64Data = pdfURL.split(',')[1];
const binaryData = atob(base64Data);
const bytes = new Uint8Array(binaryData.length);
for (let i = 0; i < binaryData.length; i++) {
bytes[i] = binaryData.charCodeAt(i);
}
}, []);
const loadingTask = pdfjs.getDocument({ data: bytes });
const pdf = await loadingTask.promise;
// Get only the specified page
const page = await pdf.getPage(currDocPage);
const textContent = await page.getTextContent();
// Filter out non-text items and assert proper type
const textItems = textContent.items.filter((item): item is TextItem =>
'str' in item && 'transform' in item
);
// Group text items into lines based on their vertical position
const tolerance = 2;
const lines: TextItem[][] = [];
let currentLine: TextItem[] = [];
let currentY: number | null = null;
textItems.forEach((item) => {
const y = item.transform[5];
if (currentY === null) {
currentY = y;
currentLine.push(item);
} else if (Math.abs(y - currentY) < tolerance) {
currentLine.push(item);
} else {
lines.push(currentLine);
currentLine = [item];
currentY = y;
}
});
lines.push(currentLine);
// Process each line to build text
let pageText = '';
for (const line of lines) {
// Sort items horizontally within the line
line.sort((a, b) => a.transform[4] - b.transform[4]);
let lineText = '';
let prevItem: TextItem | null = null;
for (const item of line) {
if (!prevItem) {
lineText = item.str;
} else {
const prevEndX = prevItem.transform[4] + (prevItem.width ?? 0);
const currentStartX = item.transform[4];
const space = currentStartX - prevEndX;
// Add space if gap is significant, otherwise concatenate directly
if (space > ((item.width ?? 0) * 0.3)) {
lineText += ' ' + item.str;
} else {
lineText += item.str;
}
}
prevItem = item;
}
pageText += lineText + ' ';
}
return pageText.replace(/\s+/g, ' ').trim();
} catch (error) {
console.error('Error extracting text from PDF:', error);
throw new Error('Failed to extract text from PDF');
}
}, []);
// Load curr doc text
const loadCurrDocText = useCallback(async () => {
@ -267,18 +267,18 @@ export function PDFProvider({ children }: { children: ReactNode }) {
console.error('Failed to get document URL:', error);
setError('Failed to retrieve the document. Please try again.');
}
}, [getDocument, loadCurrDocText]);
}, [getDocument]);
const clearCurrDoc = useCallback(() => {
setCurrDocName(undefined);
setCurrDocURL(undefined);
setCurrDocText(undefined);
setCurrDocPages(undefined);
// Clear TTS text
setCurrDocPages(undefined); // Goes to TTS context
setTTSText('');
}, []);
}, [setCurrDocPages, setTTSText]);
// Clear all highlights in the PDF viewer
const clearHighlights = useCallback(() => {