mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-07-09 12:54:47 +08:00
### What problem does this PR solve? This PR adds comprehensive **Right-to-Left (RTL) language support**, primarily targeting Arabic and other RTL scripts (Hebrew, Persian, Urdu, etc.). Previously, RTL content had multiple rendering issues: - Incorrect sentence splitting for Arabic punctuation in citation logic - Misaligned text in chat messages and markdown components - Improper positioning of blockquotes and “think” sections - Incorrect table alignment - Citation placement ambiguity in RTL prompts - UI layout inconsistencies when mixing LTR and RTL text This PR introduces backend and frontend improvements to properly detect, render, and style RTL content while preserving existing LTR behavior. #### Backend - Updated sentence boundary regex in `rag/nlp/search.py` to include Arabic punctuation: - `،` (comma) - `؛` (semicolon) - `؟` (question mark) - `۔` (Arabic full stop) - Ensures citation insertion works correctly in RTL sentences. - Updated citation prompt instructions to clarify citation placement rules for RTL languages. #### Frontend - Introduced a new utility: `text-direction.ts` - Detects text direction based on Unicode ranges. - Supports Arabic, Hebrew, Syriac, Thaana, and related scripts. - Provides `getDirAttribute()` for automatic `dir` assignment. - Applied dynamic `dir` attributes across: - Markdown rendering - Chat messages - Search results - Tables - Hover cards and reference popovers - Added proper RTL styling in LESS: - Text alignment adjustments - Blockquote border flipping - Section indentation correction - Table direction switching - Use of `<bdi>` for figure labels to prevent bidirectional conflicts #### DevOps / Environment - Added Windows backend launch script with retry handling. - Updated dependency metadata. - Adjusted development-only React debugging behavior. --- ### Type of change - [x] Bug Fix (non-breaking change which fixes RTL rendering and citation issues) - [x] New Feature (non-breaking change which adds RTL detection and dynamic direction handling) --------- Co-authored-by: 6ba3i <isbaaoui09@gmail.com> Co-authored-by: Ahmad Intisar <ahmadintisar@Ahmads-MacBook-M4-Pro.local> Co-authored-by: Ahmad Intisar <168020872+ahmadintisar@users.noreply.github.com> Co-authored-by: Liu An <asiro@qq.com>
102 lines
2.7 KiB
TypeScript
102 lines
2.7 KiB
TypeScript
/**
|
|
* RTL (Right-to-Left) text direction utilities
|
|
* Supports Arabic, Hebrew, Persian/Farsi, Urdu, and other RTL scripts
|
|
*/
|
|
|
|
// Unicode ranges for RTL scripts
|
|
const RTL_RANGES: [number, number][] = [
|
|
[0x0600, 0x06ff], // Arabic
|
|
[0x0750, 0x077f], // Arabic Supplement
|
|
[0x08a0, 0x08ff], // Arabic Extended-A
|
|
[0xfb50, 0xfdff], // Arabic Presentation Forms-A
|
|
[0xfe70, 0xfeff], // Arabic Presentation Forms-B
|
|
[0x0590, 0x05ff], // Hebrew
|
|
[0xfb1d, 0xfb4f], // Hebrew Presentation Forms
|
|
[0x0700, 0x074f], // Syriac
|
|
[0x0780, 0x07bf], // Thaana (Maldivian)
|
|
[0x0840, 0x085f], // Mandaic
|
|
[0x0860, 0x086f], // Syriac Supplement
|
|
];
|
|
|
|
/**
|
|
* Check if a character code is in RTL Unicode range
|
|
*/
|
|
const isRTLCharCode = (charCode: number): boolean => {
|
|
return RTL_RANGES.some(
|
|
([start, end]) => charCode >= start && charCode <= end,
|
|
);
|
|
};
|
|
|
|
/**
|
|
* Find the first "strong" directional character in text
|
|
* Strong characters are letters (not numbers, punctuation, or whitespace)
|
|
* Returns 'rtl', 'ltr', or 'neutral' if no strong character found
|
|
*/
|
|
export const getTextDirection = (text: string): 'rtl' | 'ltr' | 'neutral' => {
|
|
if (!text) return 'neutral';
|
|
|
|
for (const char of text) {
|
|
const code = char.charCodeAt(0);
|
|
|
|
// Skip whitespace, numbers, and common punctuation
|
|
if (
|
|
code <= 0x40 || // Control chars, digits, basic punctuation
|
|
(code >= 0x5b && code <= 0x60) || // [ \ ] ^ _ `
|
|
(code >= 0x7b && code <= 0x7f) // { | } ~ DEL
|
|
) {
|
|
continue;
|
|
}
|
|
|
|
// Check if RTL
|
|
if (isRTLCharCode(code)) {
|
|
return 'rtl';
|
|
}
|
|
|
|
// If we found a non-RTL letter, it's LTR
|
|
// Latin, Greek, Cyrillic, etc.
|
|
if (
|
|
(code >= 0x41 && code <= 0x5a) || // A-Z
|
|
(code >= 0x61 && code <= 0x7a) || // a-z
|
|
(code >= 0x00c0 && code <= 0x024f) || // Latin Extended
|
|
(code >= 0x0370 && code <= 0x03ff) || // Greek
|
|
(code >= 0x0400 && code <= 0x04ff) // Cyrillic
|
|
) {
|
|
return 'ltr';
|
|
}
|
|
}
|
|
|
|
return 'neutral';
|
|
};
|
|
|
|
/**
|
|
* Check if text contains any RTL characters
|
|
* Useful for detecting mixed content
|
|
*/
|
|
export const containsRTL = (text: string): boolean => {
|
|
if (!text) return false;
|
|
|
|
for (const char of text) {
|
|
if (isRTLCharCode(char.charCodeAt(0))) {
|
|
return true;
|
|
}
|
|
}
|
|
return false;
|
|
};
|
|
|
|
/**
|
|
* Check if text is predominantly RTL
|
|
* Returns true if first strong character is RTL
|
|
*/
|
|
export const isRTL = (text: string): boolean => {
|
|
return getTextDirection(text) === 'rtl';
|
|
};
|
|
|
|
/**
|
|
* Get the appropriate dir attribute value for HTML elements
|
|
* Returns 'rtl', 'ltr', or 'auto' (for neutral/mixed content)
|
|
*/
|
|
export const getDirAttribute = (text: string): 'rtl' | 'ltr' | 'auto' => {
|
|
const direction = getTextDirection(text);
|
|
return direction === 'neutral' ? 'auto' : direction;
|
|
};
|